© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38578
    Prev
    Next
    INDEX
    Explanations

    village or neighborhood descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oom
    -0.09
    éķĢéĶĮ
    -0.08
    _weak
    -0.08
    kor
    -0.08
    çıĬçijļ
    -0.07
    çİĭåħĪçĶŁ
    -0.07
    GED
    -0.07
    itative
    -0.07
    jal
    -0.07
    èĵIJ
    -0.07
    POSITIVE LOGITS
    娼
    0.09
    ä¸įå°ı
    0.09
    bard
    0.09
    åªĴ
    0.09
    å¦ĩ
    0.09
    å¾Ģä¸Ĭ
    0.09
     shotgun
    0.08
    èĩ³ä¸Ĭ
    0.08
    FI
    0.08
     доÑģÑĤ
    0.08
    Activations Density 0.135%

    No Known Activations