© 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. 50679
    Prev
    Next
    INDEX
    Explanations

    Ottoman, stool, bench

    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
    çĶµåı°
    -0.11
    lust
    -0.09
     ÑıвлÑı
    -0.09
    ivity
    -0.09
    ä»ĸå¦Ī
    -0.09
    worthy
    -0.09
     NIGHT
    -0.08
    æ°ĹãģĮ
    -0.08
    ycz
    -0.08
    ondo
    -0.08
    POSITIVE LOGITS
    åĩ³
    0.11
    å¢ŀåĢ¼
    0.09
    athan
    0.08
    indle
    0.08
    æµı
    0.08
    aka
    0.08
    è·º
    0.08
     stool
    0.08
    认è´Ń
    0.08
    裤åŃIJ
    0.08
    Activations Density 0.006%

    No Known Activations