© 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. 19319
    Prev
    Next
    INDEX
    Explanations

    to examine, promote, allow, facilitate, provide

    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
     ведÑĮ
    -0.09
    è¦ģä¹Ī
    -0.08
    娴
    -0.08
    为æĪij们
    -0.08
    æĺ¯åIJ¦åŃĺåľ¨
    -0.08
    ä¿Ĺ称
    -0.08
    lyn
    -0.08
    áĢļ
    -0.08
    .Raw
    -0.08
    çĶĦ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.10
    å°±éľĢè¦ģ
    0.09
    Inlining
    0.09
    å°±å¿ħé¡»
    0.09
    请è¾ĵåħ¥
    0.09
    羣æŃ£åģļåĪ°
    0.09
    å°½åı¯èĥ½
    0.08
     необÑħодимо
    0.08
     ×ķ׾×Ķ
    0.08
    æ¡£
    0.08
    Activations Density 0.226%

    No Known Activations