© 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. 63231
    Prev
    Next
    INDEX
    Explanations

    so

    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
    åIJİåį«
    -0.27
    çĪ¶æ¯į
    -0.26
    ammer
    -0.26
    uer
    -0.25
    arkers
    -0.25
    inct
    -0.25
    ="/">
    -0.25
     Navbar
    -0.24
     Saying
    -0.24
    ptime
    -0.24
    POSITIVE LOGITS
    èĭ¥æĤ¨
    0.26
    *)_
    0.25
     MULT
    0.25
     haunt
    0.25
    *q
    0.25
    @Json
    0.25
    Ñīий
    0.24
     @_
    0.24
    éĶ¢
    0.24
    秣éĩij
    0.24
    Activations Density 68.551%

    No Known Activations