© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39611
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    tes
    -0.11
    	TokenName
    -0.11
    ãģ¤ãģ®
    -0.10
    enco
    -0.10
    ëĭĺ
    -0.10
    ural
    -0.10
    ive
    -0.10
    она
    -0.09
    èĭ¥å¹²
    -0.09
     ÑĤÑĭÑģÑı
    -0.09
    POSITIVE LOGITS
    th
    0.13
    acity
    0.12
    chair
    0.10
     Downing
    0.10
    å¹´éĹ´
    0.09
    acious
    0.09
     thợ
    0.08
    erness
    0.08
     Ø¢ÙĦاÙģ
    0.08
    stra
    0.08
    Activations Density 0.272%

    No Known Activations