© 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. 22559
    Prev
    Next
    INDEX
    Explanations

    listed

    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
    ooter
    -0.29
    itur
    -0.27
     examiner
    -0.27
    çĶ³
    -0.25
    ipsis
    -0.24
     siendo
    -0.24
    ç¢İ
    -0.24
    ä¸įèµ·
    -0.24
    FSIZE
    -0.24
     depth
    -0.23
    POSITIVE LOGITS
     Carol
    0.31
     GetType
    0.28
    car
    0.28
    èĥĮæĻ¯
    0.28
    classed
    0.28
     car
    0.27
    (lo
    0.26
    lov
    0.26
    Carol
    0.25
    .Produ
    0.25
    Activations Density 0.012%

    No Known Activations