© 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. 32-TRANSCODER-HP
    7. 43943
    Prev
    Next
    INDEX
    Explanations

    Technical or mixed content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    play
    -0.29
     rele
    -0.26
    (play
    -0.25
    /mac
    -0.25
     hood
    -0.25
    ähr
    -0.25
    aha
    -0.25
    .it
    -0.24
     play
    -0.24
    ç¨Ģ
    -0.24
    POSITIVE LOGITS
    主治
    0.27
    ä¹ĭéģĵ
    0.26
    overlap
    0.26
    ä¸ĢåŃĹ
    0.25
    产ä¸ļéĽĨèģļ
    0.24
    asti
    0.24
     overlaps
    0.24
    à¤Ĥ
    0.24
    éĩįä¸Ń
    0.24
    .Serializable
    0.23
    Activations Density 0.001%

    No Known Activations