© 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. 35-TRANSCODER-HP
    7. 38686
    Prev
    Next
    INDEX
    Explanations

    Ed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ager
    -0.36
    ale
    -0.35
    ices
    -0.33
    acle
    -0.33
    ance
    -0.32
    arith
    -0.31
    eer
    -0.30
    atory
    -0.30
    ack
    -0.30
    orate
    -0.30
    POSITIVE LOGITS
     Ed
    0.36
     ed
    0.34
    .ed
    0.32
     edi
    0.31
    Ed
    0.31
    -ed
    0.30
     edt
    0.30
    (ed
    0.29
    >d
    0.29
    .Ed
    0.28
    Activations Density 0.040%

    No Known Activations