© 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. 29206
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ä¸ĭä¸Ģ个
    -0.27
    èĥ½éĩı
    -0.26
    transfer
    -0.26
    窥
    -0.25
    åĪĴ
    -0.25
    å¥ĩ
    -0.25
    ä¸Ģ次次
    -0.24
    (()=>{↵
    -0.24
    ittings
    -0.24
    éĩįä»»
    -0.24
    POSITIVE LOGITS
    ira
    0.28
     familiar
    0.26
     Pattern
    0.26
     bounty
    0.25
    _board
    0.25
     composition
    0.25
    alth
    0.24
    examples
    0.24
    erah
    0.24
    azu
    0.24
    Activations Density 1.308%

    No Known Activations