© 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. 99195
    Prev
    Next
    INDEX
    Explanations

    Internet addresses and code

    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
    Negative Logits
     nature
    -0.30
     Nature
    -0.29
    nature
    -0.27
    转
    -0.26
    ement
    -0.26
    æķ´ä½ĵ
    -0.25
    表éĿ¢ä¸Ĭ
    -0.25
    WithType
    -0.25
    Nature
    -0.25
     At
    -0.25
    POSITIVE LOGITS
    è¯·ä½ł
    0.32
    abama
    0.26
    ä¸įäºĨ
    0.26
    adle
    0.25
     Chiefs
    0.25
    onymous
    0.25
    anas
    0.24
    леж
    0.24
     OPER
    0.23
    ragen
    0.23
    Activations Density 0.016%

    No Known Activations