© 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. 9-TRANSCODER-HP
    7. 29401
    Prev
    Next
    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģæī¹
    -0.29
    erot
    -0.28
     lik
    -0.27
    ERM
    -0.26
    ä¸ĢèĦļ
    -0.24
    ä½łè¯´
    -0.24
    polit
    -0.23
    isma
    -0.23
    eron
    -0.23
    sticky
    -0.23
    POSITIVE LOGITS
    coe
    0.28
    Perl
    0.25
     still
    0.25
    äºĮåŃĹ
    0.25
    ник
    0.25
     PTS
    0.24
    ONGL
    0.24
     Carl
    0.24
    æĹ¥å¤ľ
    0.23
     [,
    0.23
    Activations Density 0.628%

    No Known Activations