© 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. 34297
    Prev
    Next
    INDEX
    Explanations

    'ack', 'arc', 'ark', 'sarc'

    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
    è¦ģ好好
    -0.09
    ako
    -0.09
     grand
    -0.09
    rale
    -0.09
    grand
    -0.09
    å·´æĸ¯
    -0.09
    ascal
    -0.09
    SES
    -0.08
    æĹ¶è¡¨ç¤º
    -0.08
     sonst
    -0.08
    POSITIVE LOGITS
    lessly
    0.10
    ful
    0.09
    ored
    0.09
    çĻ¾å§ĵ
    0.09
    gy
    0.08
    éļĻ
    0.08
    geme
    0.08
    æĦŁåºĶ
    0.08
    irma
    0.08
    çĦ¶
    0.08
    Activations Density 0.002%

    No Known Activations