© 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. 30230
    Prev
    Next
    INDEX
    Explanations

    town names following 'wood' or 'side'

    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
    èĦ±ç¦»
    -0.09
    以ä¸ĬçļĦ
    -0.08
    hare
    -0.08
    ÑĪед
    -0.08
    _fu
    -0.07
     Merch
    -0.07
    èĦ¸
    -0.07
    hall
    -0.07
    é¢Ħå¤ĩ
    -0.07
    åħ¶ä»ĸçļĦ
    -0.07
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.10
    è§Ħ模æľĢ大
    0.09
    å½ĵåľ°æŶéĹ´
    0.09
    ä¹ĭ乡
    0.09
    é²²
    0.09
    ç´ł
    0.09
    巴士
    0.09
    åĽ½æ°ij
    0.09
    rous
    0.08
    æĭ³
    0.08
    Activations Density 0.111%

    No Known Activations