© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26375
    Prev
    Next
    INDEX
    Explanations

    import related actions

    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
    eworld
    -0.09
    âľį
    -0.09
    以æѤ
    -0.09
    ouse
    -0.08
    PCS
    -0.08
    æ¦ľæł·
    -0.08
    tract
    -0.08
    西åįĹ
    -0.08
    å¼ĵ
    -0.08
    ÑĢÑı
    -0.08
    POSITIVE LOGITS
    ighb
    0.09
    åĩºæīĭ
    0.09
    gran
    0.09
    èµĽåĮº
    0.09
    ä¼ĺ
    0.09
    åıĪ好
    0.08
    getter
    0.08
     cru
    0.08
    aint
    0.08
    ä½³
    0.08
    Activations Density 0.004%

    No Known Activations