© 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. 20212
    Prev
    Next
    INDEX
    Explanations

    separating sand, feed, vibrating table

    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
    çĩĶ
    -0.11
    дей
    -0.10
    æ²Ľ
    -0.10
    egie
    -0.10
    çĻ½è¡£
    -0.09
    æľķ
    -0.09
    交ä¼ļ
    -0.09
    ","","
    -0.09
    igation
    -0.09
    åĪĨéĶĢ
    -0.08
    POSITIVE LOGITS
    çł´ç¢İ
    0.10
    é¢ļ
    0.10
    ä½ľä¸ļ
    0.10
     crusher
    0.10
    éĻ¤å°ĺ
    0.09
    çŃĽ
    0.09
    åĩıéĢŁ
    0.09
    è£ħå¤ĩ
    0.09
    èħŃ
    0.08
    æĸĻ
    0.08
    Activations Density 0.152%

    No Known Activations