© 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. 50377
    Prev
    Next
    INDEX
    Explanations

    names like Nigel, Derek, Stefan, Colin

    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
    uation
    -0.10
    ining
    -0.10
    ¶
    -0.09
    ãģªãģı
    -0.09
    usz
    -0.09
    ances
    -0.08
    ðŁı»
    -0.08
    ernational
    -0.08
    per
    -0.08
    ste
    -0.08
    POSITIVE LOGITS
    ãģ¹ãģį
    0.13
    thon
    0.12
    edList
    0.09
    ä¸įéĶĪ
    0.09
    hood
    0.09
    ãģıãĤĮ
    0.09
    ä¸Ģå¼Ģå§ĭå°±
    0.09
    佬
    0.09
     dõi
    0.09
    ãģĭãĤĭ
    0.09
    Activations Density 0.157%

    No Known Activations