© 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. 22713
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    åŁºå»º
    -0.27
    æĬĬ她
    -0.26
     dismiss
    -0.24
    ;base
    -0.24
    sville
    -0.23
    매
    -0.23
    uien
    -0.23
    IFI
    -0.23
    ifique
    -0.23
    èĤĺ
    -0.23
    POSITIVE LOGITS
    祸
    0.31
    ought
    0.29
    ä¸įåĨįæĺ¯
    0.27
    éĴĩ
    0.26
    åıĺå¾Ĺ
    0.26
    ceiver
    0.26
    Ùİا
    0.25
    urable
    0.25
    åıĺå¾ĹæĽ´åĬł
    0.25
     Earth
    0.25
    Activations Density 0.005%

    No Known Activations