© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98028
    Prev
    Next
    INDEX
    Explanations

    Names in legal/code contexts

    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
    SOC
    -0.25
    .routing
    -0.24
    details
    -0.24
    ä¸Ģ个å°ıæŶ
    -0.23
    ä¸ĭå·´
    -0.23
    åľ°ä¸ĭ
    -0.23
    _gap
    -0.23
    (sec
    -0.23
    ç¾İæľ¯é¦Ĩ
    -0.23
    iro
    -0.22
    POSITIVE LOGITS
    slaught
    0.28
    ä¸Ģç»ı
    0.27
     carp
    0.27
     dispens
    0.25
    ña
    0.25
     curs
    0.25
    itta
    0.25
     WARRANTY
    0.24
    olah
    0.24
    èģĮ
    0.24
    Activations Density 0.100%

    No Known Activations