© 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. 53602
    Prev
    Next
    INDEX
    Explanations

    on the

    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
    ä»Ģä¹Īåij¢
    -0.09
    èĢģçĪ·
    -0.09
    æ°´çĶµ
    -0.09
    vely
    -0.08
    åĩºåħ¥
    -0.08
    ANC
    -0.08
    æľĢåIJİ
    -0.08
    tems
    -0.08
    èĩªå·±åĸľæ¬¢
    -0.08
    ãĤªãĥ¼
    -0.08
    POSITIVE LOGITS
    erie
    0.09
    _PD
    0.09
    åıijçİ°äºĨ
    0.09
    缦
    0.09
    PointerType
    0.09
    _Ptr
    0.08
    忤
    0.08
    åľ¨çĶŁæ´»ä¸Ń
    0.08
    ento
    0.08
    .uk
    0.08
    Activations Density 0.031%

    No Known Activations