© 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. 88656
    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
     оÑĤд
    -0.25
    溺
    -0.25
    atus
    -0.25
    meld
    -0.25
    uli
    -0.24
    æĪªæŃ¢
    -0.24
    åĩij
    -0.23
     recap
    -0.23
    åĴ±
    -0.23
    å°±è·Ł
    -0.23
    POSITIVE LOGITS
    |i
    0.28
    _due
    0.27
    iage
    0.27
    кол
    0.26
     Utf
    0.26
    chaft
    0.25
    Due
    0.25
    èĩªç§°
    0.24
    ovich
    0.24
    æ¾İæ¹ĥæĸ°éĹ»
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.