© 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. 53133
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
     grows
    -0.28
    plug
    -0.28
     Growth
    -0.26
    pl
    -0.26
    singular
    -0.25
    Burn
    -0.25
     Wax
    -0.25
    embr
    -0.25
     pl
    -0.25
    aber
    -0.24
    POSITIVE LOGITS
    ilee
    0.30
    -fw
    0.27
    æĥľ
    0.25
    åĿij
    0.25
    ingroup
    0.24
    åīįèĢħ
    0.24
     swe
    0.24
    ä¸ĢåłĨ
    0.24
    ibu
    0.24
    soles
    0.24
    Activations Density 0.033%

    No Known Activations