© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54264
    Prev
    Next
    INDEX
    Explanations

    related to publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endant
    -0.28
    setLayout
    -0.27
    ibilit
    -0.27
     reap
    -0.27
    ivated
    -0.26
    ippers
    -0.26
    UMENT
    -0.25
     ------------------------------------------------------------------------↵
    -0.25
    ificant
    -0.24
    ashion
    -0.24
    POSITIVE LOGITS
     pubb
    0.37
     public
    0.36
    public
    0.34
    çľĭæĿ¥
    0.32
     illustrated
    0.32
     presented
    0.32
     pub
    0.31
    åħ¬åħ±
    0.31
     indicated
    0.31
     published
    0.31
    Activations Density 0.041%

    No Known Activations