© 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. 33850
    Prev
    Next
    INDEX
    Explanations

    organization services

    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
    æ»Ķ
    -0.08
    ients
    -0.08
    è¯ģåĪ¸äº¤æĺĵ
    -0.08
    æĶ»åĿļ
    -0.08
    æ·±åĮĸæĶ¹éĿ©
    -0.08
     ÑģовеÑĢÑĪ
    -0.08
    ëĭ´
    -0.08
    REAK
    -0.08
    еÑģÑĤÑĮ
    -0.08
    ä¸įçĶĺ
    -0.08
    POSITIVE LOGITS
    èµĽäºĭ
    0.15
    åĻ¨æĿIJ
    0.15
    åľºåľ°
    0.15
    èµĽåŃ£
    0.14
    èģĶèµĽ
    0.13
    ä½ĵèĤ²
    0.12
     feder
    0.12
    çļĦæ¯ĶèµĽ
    0.12
    æķĻç»ĥ
    0.11
     Indoor
    0.11
    Activations Density 0.127%

    No Known Activations