© 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. 112987
    Prev
    Next
    INDEX
    Explanations

    Cohen

    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
    á»IJ
    -0.29
    ä¸İåıijå±ķ
    -0.26
    leston
    -0.24
    ately
    -0.24
    ί
    -0.24
     own
    -0.24
    -by
    -0.23
     Hind
    -0.23
    以æĿ¥
    -0.23
    DetailsService
    -0.23
    POSITIVE LOGITS
    reau
    0.33
    qv
    0.27
    ymes
    0.26
    zer
    0.25
    пÑĢе
    0.25
     surv
    0.25
    è´¢å¯Į
    0.24
    berg
    0.24
    issance
    0.24
    egal
    0.23
    Activations Density 0.022%

    No Known Activations