© 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. 30-TRANSCODER-HP
    7. 94936
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    [string
    -0.33
    ,string
    -0.32
     string
    -0.30
    (string
    -0.28
    params
    -0.28
    [method
    -0.27
    string
    -0.27
    è¿ĺå°Ĩ
    -0.27
    	string
    -0.26
     stead
    -0.25
    POSITIVE LOGITS
    atorio
    0.25
    åľ¨æ·±åľ³
    0.25
    atoria
    0.25
    ibaba
    0.24
    ibili
    0.24
    lec
    0.23
    loid
    0.23
    æ»ĺ
    0.23
    å£ķ
    0.23
    hec
    0.23
    Activations Density 0.982%

    No Known Activations