© 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. 20257
    Prev
    Next
    INDEX
    Explanations

    purchase context and items

    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
     à¹Ĩ
    -0.11
    à¹Ĩ
    -0.11
    oli
    -0.11
    est
    -0.10
    /she
    -0.10
    ãģĹãģı
    -0.10
     ë¶Ī구íķĺê³ł
    -0.10
    ork
    -0.09
    æł·çļĦ
    -0.09
    aira
    -0.09
    POSITIVE LOGITS
    eer
    0.13
    able
    0.11
    ably
    0.10
    lements
    0.10
    ABLE
    0.10
    cy
    0.10
    ivity
    0.10
    باØŃ
    0.09
    å®Įæ¯ķ
    0.09
    æ®Ĩ
    0.09
    Activations Density 0.018%

    No Known Activations