© 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. 30192
    Prev
    Next
    INDEX
    Explanations

    addictive

    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
     repar
    -0.28
    ä¿®å¤į
    -0.27
    ä¿®
    -0.26
    åĮ¹
    -0.26
    stash
    -0.25
    ringe
    -0.25
     rehab
    -0.24
     glue
    -0.24
    @qq
    -0.24
    骡
    -0.24
    POSITIVE LOGITS
    ansa
    0.28
    aned
    0.27
    Tre
    0.27
    ç¯ĩ
    0.26
    trusted
    0.26
     Nor
    0.26
    drops
    0.26
    ikes
    0.26
    Nor
    0.25
    antino
    0.25
    Activations Density 1.375%

    No Known Activations