© 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. 29433
    Prev
    Next
    INDEX
    Explanations

    sanctuary, refuge

    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
    à¹īà¸ĩ
    -0.30
    à¹īาà¸ĩ
    -0.26
    mins
    -0.25
    è¯Ń
    -0.24
    chia
    -0.24
    wald
    -0.24
    TokenType
    -0.24
    .assert
    -0.24
    缸åĬ©
    -0.23
    iali
    -0.23
    POSITIVE LOGITS
    /oct
    0.26
     Oval
    0.26
    dia
    0.26
    cycle
    0.26
     Tet
    0.26
    ä¸ĢåĢĭ人
    0.24
    éĺģ
    0.24
    导è´Ń
    0.24
    Looper
    0.24
    arpa
    0.24
    Activations Density 2.481%

    No Known Activations