© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29261
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     WHO
    -0.28
     #↵↵
    -0.26
    WHO
    -0.25
     qui
    -0.24
    åħ±åIJĮ
    -0.24
    yst
    -0.24
    xFFFFFF
    -0.24
    æѤå¤Ħ
    -0.24
    RES
    -0.24
    bid
    -0.24
    POSITIVE LOGITS
     circumcision
    0.26
    rophe
    0.26
    chart
    0.25
    è¡ĮæĶ¿å¤Ħç½ļ
    0.25
     antid
    0.25
    èĢĺ
    0.25
    åĶIJ
    0.24
    isé
    0.24
    Ĥ¬
    0.24
     Theta
    0.23
    Activations Density 1.447%

    No Known Activations