© 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. 39574
    Prev
    Next
    INDEX
    Explanations

    Redwood and cypress parks

    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
    ellation
    -0.10
    çķª
    -0.09
    icker
    -0.09
    (variable
    -0.09
    баÑĢ
    -0.09
    çŁ³çģ°
    -0.08
    förder
    -0.08
    åIJı
    -0.08
    edly
    -0.08
    anim
    -0.08
    POSITIVE LOGITS
    åŁķ
    0.09
    主é¢ĺ
    0.09
    ç¯ĩç«ł
    0.09
     terr
    0.09
    æ·±åĪĩ
    0.08
    åįĥå¹´
    0.08
    FP
    0.08
    å¾Ĥ
    0.08
     Disp
    0.08
     pec
    0.08
    Activations Density 0.003%

    No Known Activations