© 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. 35211
    Prev
    Next
    INDEX
    Explanations

    won

    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
    åĩºè·¯
    -0.10
    é¢Ĩ
    -0.09
    è§ĦèĮĥ
    -0.09
    çĶij
    -0.09
    帳
    -0.09
    龸
    -0.09
    é¦Ĭ
    -0.09
    ä¼łéĢģ
    -0.09
    odont
    -0.09
    æĿ¥è¿Ľè¡Į
    -0.09
    POSITIVE LOGITS
    é¦Ļæ°´
    0.10
    票
    0.09
    ths
    0.09
     cá»Ń
    0.08
    èµ¢
    0.08
    溪
    0.08
    åij±
    0.08
    å¹ħ度
    0.08
    idy
    0.08
    amas
    0.07
    Activations Density 0.105%

    No Known Activations