© 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. 10286
    Prev
    Next
    INDEX
    Explanations

    free software

    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
    æį¢åıĸ
    -0.10
    æĪijèĩªå·±
    -0.10
    åĩłæ¬¡
    -0.09
     ÑĢанее
    -0.09
    äºĨä¸Ģéģį
    -0.09
    åĺ´éĩĮ
    -0.09
    家ä¼Ļ
    -0.09
    LayoutManager
    -0.08
    æľĢåħ³éĶ®çļĦ
    -0.08
    gether
    -0.08
    POSITIVE LOGITS
    /is
    0.10
    ÙĪÙĨ
    0.10
    å¾Ĺå¾Ī
    0.10
    /w
    0.10
    个å¤ļ
    0.09
    olate
    0.09
    è¿Ļæł·è¯´
    0.09
     gì
    0.09
    俺
    0.09
    rael
    0.08
    Activations Density 1.077%

    No Known Activations