© 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. 61859
    Prev
    Next
    INDEX
    Explanations

    location and demographic contexts

    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
    ç¾İ好çĶŁæ´»
    -0.11
    è´¶
    -0.10
    åŃĺéĩı
    -0.10
    è¿ĻåĿĹ
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    ·»
    -0.09
    èĩªçĦ¶æĺ¯
    -0.09
    combe
    -0.09
    éĻªçĿĢ
    -0.09
    èĥŀ
    -0.08
    POSITIVE LOGITS
    å¯¹ä½ł
    0.08
     Hass
    0.08
    els
    0.08
    alion
    0.08
    QS
    0.08
    éļıå¤Ħ
    0.08
    æĪĸå¤ļ
    0.08
    ACE
    0.08
    è¿Ľé¡¹
    0.08
    严éĩį
    0.08
    Activations Density 0.223%

    No Known Activations