© 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. 21961
    Prev
    Next
    INDEX
    Explanations

    possible options or alternatives

    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
    åıijçİ°äºĨ
    -0.09
    å¢ħ
    -0.09
     Braz
    -0.09
    æīįåıijçİ°
    -0.09
    交ä»ĺ
    -0.08
    kek
    -0.08
    åıªå¥½
    -0.08
    åĬ¡å¿ħ
    -0.08
    两åı¥
    -0.08
    .sul
    -0.08
    POSITIVE LOGITS
    åı¯èĥ½æĢ§
    0.20
    çļĦåı¯èĥ½æĢ§
    0.17
     possibility
    0.14
     possibilities
    0.14
    æľīåı¯èĥ½
    0.11
    æĦŁåħ´è¶£
    0.11
     ê°ĢëĬ¥ìĦ±
    0.11
     возможноÑģÑĤи
    0.11
     possible
    0.10
     POSS
    0.10
    Activations Density 0.085%

    No Known Activations