© 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. 22503
    Prev
    Next
    INDEX
    Explanations

    asm

    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
    owns
    -0.26
    si
    -0.26
    --------------------------------------------------------------------------↵
    -0.25
    åı·çº¿
    -0.25
    sel
    -0.24
     element
    -0.24
    ä¸įä¸Ĭ
    -0.24
    æĦŁ
    -0.24
    æ¡Ī
    -0.24
    æľīéĴĪ对æĢ§
    -0.24
    POSITIVE LOGITS
    uese
    0.26
    .mass
    0.26
     зай
    0.25
    ãĤ¦ãĤ©
    0.24
     Guar
    0.24
     маÑģÑģ
    0.24
    庸
    0.23
    .Constraint
    0.23
     incumb
    0.23
    继
    0.23
    Activations Density 0.002%

    No Known Activations