© 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. 51308
    Prev
    Next
    INDEX
    Explanations

    required fields

    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
     Ðijа
    -0.12
    æ¦Ħ
    -0.10
    /count
    -0.09
    æ£Ĵ
    -0.09
    olar
    -0.08
    æľī幸
    -0.08
    äºĭ
    -0.08
    ãģįãģ¾ãģĹãģŁ
    -0.08
     ol
    -0.08
     SAFE
    -0.08
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.11
    å¡«åĨĻ
    0.10
    ä¸įèĥ½ä¸ºç©º
    0.10
    onian
    0.10
    çĶľçĶľ
    0.10
    .er
    0.09
     fields
    0.09
    å¿ħ
    0.09
    agt
    0.09
    utor
    0.09
    Activations Density 0.084%

    No Known Activations