© 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. 52824
    Prev
    Next
    INDEX
    Explanations

    picking without replacement

    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
    ä½łèĩªå·±
    -0.12
    ä¿Ł
    -0.11
    ä¸įçŁ¥ä¸į
    -0.10
    éĢĤåIJĪèĩªå·±
    -0.10
    uptools
    -0.10
    ç«¿
    -0.10
    溽
    -0.10
    nil
    -0.10
    ç´Ĭä¹±
    -0.10
    _RCC
    -0.10
    POSITIVE LOGITS
    8
    0.08
    6
    0.08
    2
    0.08
    7
    0.08
    0
    0.08
    9
    0.08
    4
    0.08
    1
    0.08
    5
    0.08
    LD
    0.08
    Activations Density 0.003%

    No Known Activations