© 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. 22-TRANSCODER-HP
    7. 129036
    Prev
    Next
    INDEX
    Explanations

    pay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    次ä¼ļè®®
    -0.28
    uous
    -0.28
    rost
    -0.27
    laughter
    -0.27
    pecific
    -0.24
    empre
    -0.24
     preferably
    -0.24
    IRONMENT
    -0.24
    ROID
    -0.23
    =context
    -0.23
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.28
    ç®±
    0.26
    dns
    0.25
    笺
    0.24
    åŃIJåħ¬åı¸
    0.24
    imento
    0.23
     á»ķn
    0.23
    ุà¸ĩ
    0.23
    exus
    0.23
    IMENT
    0.23
    Activations Density 0.300%

    No Known Activations