© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50934
    Prev
    Next
    INDEX
    Explanations

    granularity or texture

    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
    æ±ĩ
    -0.09
    çĹ´
    -0.09
    éĻ¡
    -0.09
     Cly
    -0.09
    losed
    -0.08
    åį³å°ĨåĪ°æĿ¥
    -0.08
    ssel
    -0.08
    rage
    -0.08
    é«ĺåĩº
    -0.08
    éĻĽ
    -0.08
    POSITIVE LOGITS
    NING
    0.10
    iba
    0.10
    NESS
    0.09
     dần
    0.09
    å¹´ä¹ĭ
    0.09
    ie
    0.08
    oftware
    0.08
    ãģıãģª
    0.08
    å¤ļå±Ĥ次
    0.08
    /fs
    0.08
    Activations Density 0.008%

    No Known Activations