© 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. 38836
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -0.34
     "
    -0.33
    ,
    -0.32
     sometimes
    -0.32
     contr
    -0.31
     a
    -0.31
     y
    -0.29
     d
    -0.29
     n
    -0.29
     all
    -0.29
    POSITIVE LOGITS
    edith
    0.29
    ç¼µ
    0.26
    DCF
    0.25
    尾巴
    0.25
    ihar
    0.25
    HING
    0.24
    oleon
    0.24
    echa
    0.24
     parametro
    0.24
    osas
    0.24
    Activations Density 27.040%

    No Known Activations

    This feature has no known activations.