© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22677
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yb
    -0.27
    æĸĩä¸Ń
    -0.25
    wen
    -0.25
    Intl
    -0.25
     Guinness
    -0.25
     Supplement
    -0.24
     Darling
    -0.24
     routine
    -0.24
    à¸ģรรม
    -0.24
    æ¯Ľ
    -0.24
    POSITIVE LOGITS
    ündig
    0.28
    pcf
    0.28
    üler
    0.28
    Å°
    0.26
    $criteria
    0.26
     Möglich
    0.25
    èģĶ
    0.25
     rozwiÄħz
    0.25
     griev
    0.24
    limits
    0.24
    Activations Density 0.000%

    No Known Activations