© 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. 40354
    Prev
    Next
    INDEX
    Explanations

    brimsec, overflowing, bronzers

    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
    è¿ĻåĿĹ
    -0.09
    æĤ²åī§
    -0.08
    ation
    -0.08
    DIST
    -0.07
    à¸ĩ
    -0.07
    éĨī
    -0.07
     door
    -0.07
     tslint
    -0.07
    AndUpdate
    -0.07
    GRE
    -0.07
    POSITIVE LOGITS
    ingly
    0.17
    èĩ¾
    0.12
    entes
    0.11
    æ¶Į
    0.11
    æ¶Įçİ°
    0.10
    psc
    0.10
    æĹºçĽĽ
    0.10
    æ¹
    0.10
    erton
    0.09
    åĭĥåĭĥ
    0.09
    Activations Density 0.009%

    No Known Activations