© 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. 111543
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    人群ä¸Ń
    -0.27
    åħ¬ç¤¾
    -0.27
    ä¾ĭåŃIJ
    -0.25
    _nat
    -0.25
    .lot
    -0.24
    lâ
    -0.24
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.24
    ä¸Ģç«Ļå¼ı
    -0.23
    çĺµ
    -0.23
     vaz
    -0.23
    POSITIVE LOGITS
    ene
    0.26
    ces
    0.26
     property
    0.25
    sit
    0.25
    urable
    0.25
    åĪ¶è£ģ
    0.24
    stop
    0.24
    éĹ°
    0.23
    ordan
    0.23
     olduk
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.