© 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. 26424
    Prev
    Next
    INDEX
    Explanations

    state changes or progression

    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
    åıĺå¾ĹæĽ´
    -0.10
    çļĦä¿¡å¿ĥ
    -0.10
    aho
    -0.09
    åıĺå¾Ĺ
    -0.09
    åĩºåİ»
    -0.09
    çļĦ梦æĥ³
    -0.09
    enticate
    -0.09
    .construct
    -0.09
    çļĦçĥŃæĥħ
    -0.09
    çļĦ羣å®ŀ
    -0.09
    POSITIVE LOGITS
    enary
    0.09
    æľīåĬ©
    0.09
    anded
    0.08
     Uni
    0.08
    è¿ĩäºĨ
    0.08
    ä¸įåħį
    0.08
    /year
    0.08
     Throwable
    0.08
    ç»´æĮģ
    0.07
    _have
    0.07
    Activations Density 0.745%

    No Known Activations