© 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. 51418
    Prev
    Next
    INDEX
    Explanations

    register before you can post

    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
    èĢIJ
    -0.10
    _dirty
    -0.09
    åľŃ
    -0.09
    ToProps
    -0.09
    ä¸įèĪį
    -0.08
    ึà¸ģ
    -0.08
    pite
    -0.08
     kra
    -0.08
    gee
    -0.08
    ible
    -0.08
    POSITIVE LOGITS
    ç©·
    0.10
     clos
    0.10
    andin
    0.09
    æīįåı¯ä»¥
    0.09
    æīįèĥ½
    0.09
    serter
    0.09
    åħ·æľīä¸Ģå®ļ
    0.09
    ENTA
    0.09
    éĺ²æ²»
    0.08
    gens
    0.08
    Activations Density 0.010%

    No Known Activations