© 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. 22311
    Prev
    Next
    INDEX
    Explanations

    Modulo operator

    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
     correspond
    -0.28
    imen
    -0.27
     Ending
    -0.26
    _invoke
    -0.26
     correspondence
    -0.26
    èķ
    -0.26
    æľįåĬ¡å¹³åı°
    -0.25
     cant
    -0.24
    ruk
    -0.24
    .ManyToManyField
    -0.24
    POSITIVE LOGITS
    åIJ¸æĶ¶
    0.29
     Familie
    0.27
    æĭ¿
    0.27
    å¸ĤåĮº
    0.26
    æ¶ĪèĢĹ
    0.26
    åİŁçIJĨ
    0.25
    oct
    0.24
     Hunter
    0.24
    æĶ¶
    0.24
    -tab
    0.24
    Activations Density 0.003%

    No Known Activations