© 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. 112805
    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
    åħ±åĴĮåĽ½
    -0.26
    vak
    -0.25
    Enumerator
    -0.24
    å®Į
    -0.23
    å¥Ĺè£ħ
    -0.23
    路段
    -0.23
     Lotus
    -0.23
    nsic
    -0.23
    ISK
    -0.23
    WAYS
    -0.22
    POSITIVE LOGITS
    绿èī²çݯä¿Ŀ
    0.29
    ARDS
    0.27
     Earn
    0.25
    .Args
    0.25
    Green
    0.25
    åį´ä¸į
    0.23
    [...,
    0.23
    çļĦæ¯į亲
    0.23
    产ä¸ļéĵ¾
    0.23
     men
    0.22
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.