© 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. 26882
    Prev
    Next
    INDEX
    Explanations

    winter vegetables, gourds, squash

    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
    hana
    -0.10
    æķıéĶIJ
    -0.09
    ìĤ¬ë¬´
    -0.09
    ä¹ŁæŃ£æĺ¯
    -0.09
    èĢ³
    -0.09
    chal
    -0.09
    æªĶ
    -0.09
    æŁľåı°
    -0.09
    主ä¹īæĢĿæĥ³
    -0.08
    зо
    -0.08
    POSITIVE LOGITS
    åįĹçĵľ
    0.11
    lect
    0.10
    åįł
    0.10
    çĵł
    0.09
     Halloween
    0.09
    getC
    0.08
    åĴ³
    0.08
     pumpkin
    0.08
    HO
    0.08
    _dump
    0.08
    Activations Density 0.041%

    No Known Activations