© 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. 29222
    Prev
    Next
    INDEX
    Explanations

    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
     deter
    -0.28
    ilton
    -0.28
    è¿İæİ¥
    -0.27
    çļĭ
    -0.26
    å¾ħ
    -0.26
     instead
    -0.25
    orns
    -0.25
    YM
    -0.25
     WebDriverWait
    -0.24
    ä¸ij
    -0.23
    POSITIVE LOGITS
    té
    0.30
     _$
    0.28
    éºĭ
    0.28
    ç»
    0.27
    è¿ĩç¨ĭå½ĵä¸Ń
    0.26
     pill
    0.25
    å¤ĸåľ°
    0.25
    {name
    0.24
    -fired
    0.24
    è§ŀ
    0.24
    Activations Density 1.596%

    No Known Activations