© 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. 56308
    Prev
    Next
    INDEX
    Explanations

    recommend or suggest actions

    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
    Ñģла
    -0.10
    èĢĮåĩº
    -0.10
    å§Ķå®£ä¼łéĥ¨
    -0.10
     cutter
    -0.10
    å®ĺ宣
    -0.09
    ä¸įæ¸ħæ¥ļ
    -0.09
    宣称
    -0.09
    宣å¸ĥ
    -0.09
    icut
    -0.09
    åıijå¸ĥäºĨ
    -0.09
    POSITIVE LOGITS
    åħĪ
    0.09
    ãģĤãĤĭç¨ĭ度
    0.09
    大家åı¯ä»¥
    0.09
    nof
    0.08
    大家
    0.08
     rằng
    0.08
    çĨ¬
    0.08
    ä½łåľ¨
    0.07
     pride
    0.07
    æĪijä»¬åľ¨
    0.07
    Activations Density 0.022%

    No Known Activations