© 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. 22113
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
    fy
    -0.09
     exper
    -0.09
    ç§Łè½¦
    -0.09
    å¨ĺ家
    -0.09
    ä¸ĵ家
    -0.09
    hammad
    -0.09
    aroo
    -0.09
    inea
    -0.08
    kit
    -0.08
    éĺµåľ°
    -0.08
    POSITIVE LOGITS
    讽
    0.09
    網
    0.09
    -frame
    0.08
    çĶµèĦij
    0.08
    tps
    0.08
    _translate
    0.08
    jaw
    0.08
     wspóÅĤ
    0.08
    æľºåħ³
    0.08
    çļ®éĿ©
    0.08
    Activations Density 0.196%

    No Known Activations