© 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. 30-TRANSCODER-HP
    7. 95216
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tear
    -0.28
    å±ģ
    -0.28
    gere
    -0.27
    ué
    -0.27
    Margins
    -0.25
    gra
    -0.25
     Nguy
    -0.24
    hq
    -0.24
    inker
    -0.24
    转载
    -0.24
    POSITIVE LOGITS
     higher
    0.29
     le
    0.27
    æ¯Ķ
    0.26
    ä¸Ģ级
    0.26
    ile
    0.26
     пеÑĢвого
    0.25
    mma
    0.25
    ç»Ī身
    0.24
    ä¸ĢéĿ¢
    0.24
     inherited
    0.23
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.