© 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. 38791
    Prev
    Next
    INDEX
    Explanations

    Val

    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
    èĻı
    -0.29
    inherits
    -0.27
    inary
    -0.27
    wipe
    -0.26
    indsight
    -0.26
     resident
    -0.25
    ollect
    -0.25
     echoed
    -0.25
    ä¹Łåıªèĥ½
    -0.25
    ictured
    -0.25
    POSITIVE LOGITS
    an
    0.33
    ma
    0.33
     Cav
    0.32
    let
    0.31
     Gard
    0.31
    çīŁ
    0.31
     An
    0.30
     Cro
    0.30
    mer
    0.30
     Sal
    0.30
    Activations Density 4.592%

    No Known Activations