© 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. 62476
    Prev
    Next
    INDEX
    Explanations

    organizing, identifying, preserving

    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
    对å¾ħ
    -0.10
    åĩłä½į
    -0.09
    ä»Ģ
    -0.09
    ınd
    -0.09
    atro
    -0.09
    åĴĭ
    -0.09
    krä
    -0.08
    éĢłåģĩ
    -0.08
    _ALT
    -0.08
    ç»ĵå±Ģ
    -0.08
    POSITIVE LOGITS
    ç¬
    0.10
    èĭĵ
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    æĩĤäºĭ
    0.09
     matters
    0.09
    äºĭå®ľ
    0.09
    æľºèĥ½
    0.09
     ÑģобÑģÑĤвенно
    0.08
    çĿ£ä¿ĥ
    0.08
    管çIJĨå·¥ä½ľ
    0.08
    Activations Density 0.155%

    No Known Activations