© 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. 26188
    Prev
    Next
    INDEX
    Explanations

    issue with

    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
    Negative Logits
    shi
    -0.09
    ers
    -0.09
    spe
    -0.08
    被èªī
    -0.08
    纪å§Ķ
    -0.08
    ci
    -0.08
    å¾Ĺä½ı
    -0.08
    è²Į
    -0.08
    馥
    -0.08
    ren
    -0.08
    POSITIVE LOGITS
    (issue
    0.12
    ราว
    0.10
    antity
    0.10
    	TokenName
    0.10
    è¿ĻäºĽéĹ®é¢ĺ
    0.10
    iginal
    0.09
    ForResult
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    gil
    0.09
    èĭ±çī¹
    0.09
    Activations Density 0.063%

    No Known Activations