© 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. 23781
    Prev
    Next
    INDEX
    Explanations

    a free

    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
    å§Ĭ妹
    -0.09
    ÐIJÐŀ
    -0.09
    äºīåıĸ
    -0.09
    æīĴ
    -0.09
    å§IJå§IJ
    -0.08
    çī²
    -0.08
    ç¥ŀåĻ¨
    -0.08
    çīĮåŃIJ
    -0.08
    æ¼ıæ°´
    -0.08
    rh
    -0.08
    POSITIVE LOGITS
    å¿ł
    0.10
    çĸ²
    0.09
    _simps
    0.09
    tees
    0.09
    umn
    0.09
     Warwick
    0.09
    getExtension
    0.08
    iques
    0.08
    ç©´
    0.08
    笼
    0.08
    Activations Density 0.002%

    No Known Activations