© 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. 97068
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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
    Ø·ÙĬ
    -0.28
    üb
    -0.28
    atrix
    -0.27
    onium
    -0.26
    åı£å¾Ħ
    -0.26
     man
    -0.25
     constituent
    -0.25
    주민
    -0.24
    âİĿ
    -0.24
    stringLiteral
    -0.24
    POSITIVE LOGITS
    past
    0.27
    串
    0.26
    ByExample
    0.25
    éĢīç§Ģ
    0.24
    æłĩé¢ĺ
    0.24
     Cups
    0.24
    çļĦä¾ĭåŃIJ
    0.24
    instances
    0.23
    å¡ij
    0.23
    æ²»çIJĨä½ĵç³»
    0.23
    Activations Density 0.008%

    No Known Activations