© 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. 30167
    Prev
    Next
    INDEX
    Explanations

    measurements per liter

    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
    ://'
    -0.28
    ansa
    -0.27
     liqu
    -0.26
    å«Įçĸij
    -0.25
    <vector
    -0.25
    è¿ĩåħ³
    -0.24
    è±ĨèħIJ
    -0.24
    çĤ³
    -0.23
    vector
    -0.23
     backtrack
    -0.23
    POSITIVE LOGITS
    åIJł
    0.25
    交äºĴ
    0.25
    ¡°
    0.24
    $request
    0.24
     Weiner
    0.24
    ield
    0.23
    ç»Ĩèħ»
    0.23
    õ
    0.23
    èĩº
    0.22
     envisioned
    0.22
    Activations Density 1.260%

    No Known Activations