© 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. 51119
    Prev
    Next
    INDEX
    Explanations

    Grasp the Sparrow’s Tail

    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
    翾
    -0.09
    æĿ¾
    -0.09
    ç¿¥
    -0.09
    æ¯Ķè¾ĥ大
    -0.09
    èī³
    -0.09
    porto
    -0.09
    æºħ
    -0.08
    èĭ¾
    -0.08
    éĢŁ
    -0.08
    æ¯Ķè¾ĥ
    -0.08
    POSITIVE LOGITS
    åĦĴ家
    0.12
    ä¸ĩçī©
    0.11
    ä¹ĭéģĵ
    0.11
    åŃĶåŃIJ
    0.10
    å¾ģä¿¡
    0.10
    æ³ķåĪĻ
    0.10
    é»į
    0.10
    çŃ®
    0.10
    æĿĸ
    0.10
    ä¸ĩäºĭ
    0.09
    Activations Density 0.022%

    No Known Activations