© 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. 33651
    Prev
    Next
    INDEX
    Explanations

    Clearance Certificate and credit

    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
    çĽ²
    -0.13
    åħ¨æĹ¥
    -0.09
    èĨ³
    -0.08
     Nested
    -0.08
    æĪijåĸľæ¬¢
    -0.08
    å¥Ĥ
    -0.08
    wel
    -0.08
     Glasses
    -0.08
    ä¼łå¯¼
    -0.08
    .Guid
    -0.08
    POSITIVE LOGITS
    å¾ģä¿¡
    0.11
    失信
    0.11
    eti
    0.10
    åĪ®
    0.10
    frey
    0.10
    agi
    0.09
    .connections
    0.09
    çĮ·
    0.09
    å¼
    0.09
    åĪijäºĭ
    0.09
    Activations Density 0.052%

    No Known Activations