© 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. 130850
    Prev
    Next
    INDEX
    Explanations

    .edu

    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
    cesso
    -0.28
    åĸľæ¬¢
    -0.26
    nine
    -0.26
    Her
    -0.25
    ned
    -0.25
    WithValue
    -0.25
    ues
    -0.24
    duk
    -0.24
    å°ĺ
    -0.24
     Passage
    -0.23
    POSITIVE LOGITS
    fect
    0.30
    çļĦä¼łç»Ł
    0.25
    -aged
    0.25
    å±IJ
    0.25
    å»ĵ
    0.25
    éĢĨ
    0.24
     traditional
    0.24
    invert
    0.24
    _POINTER
    0.23
    oples
    0.23
    Activations Density 1.076%

    No Known Activations