© 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. 97357
    Prev
    Next
    INDEX
    Explanations

    back

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢģ
    -0.29
    tern
    -0.29
    ï¼īãĢģ
    -0.28
    æĬĢæľ¯åĴĮ
    -0.28
    atre
    -0.26
    èĥ½åĬĽåĴĮ
    -0.26
    ä¼ģä¸ļåĴĮ
    -0.26
    并éĢļè¿ĩ
    -0.25
    tered
    -0.25
    )&&
    -0.24
    POSITIVE LOGITS
    rov
    0.27
    è´·
    0.26
    arpa
    0.24
    ç¾
    0.24
    appers
    0.24
    Expires
    0.24
    ä¸Ģ头
    0.23
    /rem
    0.23
    å¤Ł
    0.23
    ilon
    0.23
    Activations Density 0.019%

    No Known Activations