© 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. 18385
    Prev
    Next
    INDEX
    Explanations

    form of

    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
    ynn
    -0.10
    èĭ¥å¹²
    -0.09
    ãģĿ
    -0.09
    benh
    -0.09
    å°ıæŶåĢĻ
    -0.09
     Mant
    -0.08
    侬
    -0.08
     fri
    -0.08
    _LS
    -0.08
     cánh
    -0.08
    POSITIVE LOGITS
    å¨ģæħij
    0.11
    ç½²
    0.09
    çļĦé«ĺ度
    0.09
    uler
    0.09
    综åIJĪæ²»çIJĨ
    0.09
    社ä¼ļå®ŀè·µ
    0.09
    å¥ĸåĬ±
    0.09
    akest
    0.08
    æ¼±
    0.08
    opensource
    0.08
    Activations Density 0.040%

    No Known Activations