© 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. 31789
    Prev
    Next
    INDEX
    Explanations

    burglary and arson related crimes

    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
    ãģ£ãģįãĤĬ
    -0.11
    inent
    -0.09
    ablish
    -0.08
    rollo
    -0.08
     Lazar
    -0.08
    é¦Ĩ
    -0.08
    LINE
    -0.08
    plevel
    -0.08
    çĽijçĿ£ç®¡çIJĨ
    -0.08
    ãģľ
    -0.08
    POSITIVE LOGITS
    大æĸ¹
    0.11
    urd
    0.10
    cies
    0.10
    潦
    0.10
    ured
    0.10
    大å®Ĺ
    0.09
    窿
    0.09
    uminum
    0.09
    ä¹ĭå¤ľ
    0.09
    çĻĸ
    0.08
    Activations Density 0.006%

    No Known Activations