© 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. 57205
    Prev
    Next
    INDEX
    Explanations

    call or contact information

    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
    说ä¸įåĩº
    -0.09
    æ±Łæ¹ĸ
    -0.09
    kit
    -0.09
     Bulk
    -0.09
    åĪĨå·¥
    -0.09
    åİļéĩį
    -0.08
     fy
    -0.08
    ãĥ³ãĥī
    -0.08
     canc
    -0.08
    æ¸ļ
    -0.08
    POSITIVE LOGITS
    äºijéĽĨ
    0.10
    请èģĶç³»
    0.10
     Slam
    0.10
    _mB
    0.09
    èģĶç³»
    0.09
    ç»ļ
    0.09
    emas
    0.09
    peare
    0.09
    _CONTACT
    0.08
    麾
    0.08
    Activations Density 0.080%

    No Known Activations