© 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. 30185
    Prev
    Next
    INDEX
    Explanations

    scan

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æŶåħī
    -0.29
    .terminate
    -0.28
    æľĢåıĹ
    -0.27
    placeholders
    -0.27
    æįĤ
    -0.26
     inclusion
    -0.26
    _include
    -0.25
    åħ»èĢģ
    -0.25
    åĢ¦
    -0.24
    缣
    -0.24
    POSITIVE LOGITS
    uin
    0.28
    èıģ
    0.26
    =center
    0.26
    haar
    0.25
    itness
    0.25
    箸
    0.25
    registry
    0.25
    ç¼Ĺ
    0.24
     registry
    0.24
    uitive
    0.24
    Activations Density 2.636%

    No Known Activations