© 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. 53468
    Prev
    Next
    INDEX
    Explanations

    lists with punctuation and specific verbs

    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
    SHA
    -0.10
    寰
    -0.09
    ë§ĺ
    -0.09
    è°ħ
    -0.09
     коÑĤоÑĢаÑı
    -0.09
    å¿Ĵ
    -0.09
    åģļçļĦäºĭ
    -0.09
    anners
    -0.09
    cps
    -0.09
    assen
    -0.09
    POSITIVE LOGITS
    il
    0.09
    ãĤĿ
    0.08
     Rub
    0.08
    æ²ĵ
    0.08
    å¥ī
    0.08
    éĺĹ
    0.08
    ä»¥ä¹łè¿ijå¹³
    0.07
     Kou
    0.07
    toContain
    0.07
    iani
    0.07
    Activations Density 0.669%

    No Known Activations