© 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. 23142
    Prev
    Next
    INDEX
    Explanations

    applied to

    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
    åħ«å¤§
    -0.11
    åľ¨æķ´ä¸ª
    -0.11
    éĺģ
    -0.11
    åıijå±ķæł¼å±Ģ
    -0.10
    大èĩ´
    -0.10
    éĸ£
    -0.09
    .addRow
    -0.09
    è¿ĻåIJį
    -0.09
    è¿©
    -0.09
    èµĺ
    -0.09
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.09
    èIJ½
    0.08
    able
    0.08
     Mahm
    0.08
     полÑĥ
    0.08
    æĻļä¸Ĭ
    0.08
    èĮĥåĽ´
    0.08
    æĹłäºº
    0.07
     Clayton
    0.07
    请æ±Ĥ
    0.07
    Activations Density 0.087%

    No Known Activations