© 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. 9-TRANSCODER-HP
    7. 29134
    Prev
    Next
    INDEX
    Explanations

    containing "in"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     surf
    -0.28
    缶
    -0.28
    flow
    -0.27
    ONY
    -0.25
    çĦļ
    -0.25
    mgr
    -0.25
     Bet
    -0.25
     detected
    -0.25
    dep
    -0.25
     flow
    -0.25
    POSITIVE LOGITS
     signatures
    0.30
    æ¯ıå¹´
    0.27
     Signing
    0.27
    objectId
    0.26
    ä¸ĬäºĨ
    0.25
    é«ĺåľ°
    0.25
    ivamente
    0.25
    oose
    0.24
    çĭ¬çī¹çļĦ
    0.24
    loh
    0.23
    Activations Density 0.114%

    No Known Activations