© 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. 97154
    Prev
    Next
    INDEX
    Explanations

    order

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    walker
    -0.27
     literature
    -0.26
    çĪ¬ä¸Ĭ
    -0.26
    mailer
    -0.26
    itta
    -0.26
    kan
    -0.26
    çľĭå¾Ĺ
    -0.25
     banda
    -0.25
     reducers
    -0.25
    ĻĤ
    -0.25
    POSITIVE LOGITS
    ç»Ļ大家
    0.30
    teil
    0.28
     ÑĩÑĤобÑĭ
    0.28
    为äºĨ
    0.28
    æĺ¯ä¸ºäºĨ
    0.28
    to
    0.26
    tos
    0.26
    udeau
    0.26
     "
    0.26
     circum
    0.26
    Activations Density 0.007%

    No Known Activations