© 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. 112298
    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
    unal
    -0.26
    èĦijæµ·ä¸Ń
    -0.25
     kingdoms
    -0.25
    æ»ļæ»ļ
    -0.24
    ritis
    -0.24
    第äºĮèĬĤ
    -0.24
    åľ¨æĦı
    -0.23
    ä¸įä¿¡
    -0.23
    _roll
    -0.23
    icum
    -0.23
    POSITIVE LOGITS
    亲
    0.26
    clo
    0.26
     \%
    0.25
    ä¹Łæ¯Ķè¾ĥ
    0.25
    ä¹Łè®¸
    0.25
    å½¢
    0.25
     Eq
    0.25
    éĽĨä¸Ń
    0.25
    éļĭ
    0.25
    AndHashCode
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.