© 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. 20-TRANSCODER-HP
    7. 63472
    Prev
    Next
    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brig
    -0.27
    aque
    -0.27
    浸
    -0.27
    æģŃ
    -0.27
     fined
    -0.26
    Fine
    -0.26
    irim
    -0.26
    竦
    -0.25
    èįĴ
    -0.24
    ipient
    -0.24
    POSITIVE LOGITS
    æī£éĻ¤
    0.31
     minus
    0.30
     subtraction
    0.30
    ectl
    0.30
    æİĴéĻ¤
    0.30
    tons
    0.29
    åĩı
    0.29
    elm
    0.29
    ields
    0.29
    minus
    0.27
    Activations Density 17.140%

    No Known Activations