© 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. 50214
    Prev
    Next
    INDEX
    Explanations

    nightmare

    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
     Rac
    -0.09
    PASS
    -0.08
    mdl
    -0.08
    ä¸įéĻIJ
    -0.08
    ild
    -0.08
    æݢ索
    -0.08
    water
    -0.08
    ality
    -0.08
    ings
    -0.07
    patient
    -0.07
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.11
    åįĵ
    0.10
    éĩįéĩį
    0.10
    èĪ¬
    0.10
    ä¸ĢåĪĻ
    0.10
    å¯IJ
    0.10
    ivan
    0.10
    ä¸įçĦ¶
    0.09
    éĢļé£İ
    0.09
    turned
    0.09
    Activations Density 0.003%

    No Known Activations