© 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. 57312
    Prev
    Next
    INDEX
    Explanations

    pass or recommended

    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
    -policy
    -0.10
    ä¿Ŀå§Ĩ
    -0.09
     tip
    -0.09
     Latest
    -0.09
    æŀķ头
    -0.08
     беÑģп
    -0.08
    RequestBody
    -0.08
    amil
    -0.08
    åı¯è§Ĩ
    -0.08
    ainless
    -0.08
    POSITIVE LOGITS
    ori
    0.10
    cede
    0.10
    åĽ¡
    0.09
    人身
    0.09
    åĪ¶
    0.09
    åį±éĻ©
    0.09
     gef
    0.08
    çĸ¯
    0.08
    mad
    0.08
    å¿ĥèĦıçĹħ
    0.08
    Activations Density 0.077%

    No Known Activations