© 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. 53582
    Prev
    Next
    INDEX
    Explanations

    relapse, exacerbation

    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
    æµij
    -0.10
    éĿĽ
    -0.10
    illery
    -0.09
    è¿İæİ¥
    -0.09
     squeeze
    -0.09
    éĢIJ
    -0.09
    å¼
    -0.09
    æİ¥è¿ij
    -0.09
    溧
    -0.09
    å©´
    -0.09
    POSITIVE LOGITS
     flare
    0.13
    åıijä½ľ
    0.12
    çĪĨåıij
    0.11
    çĹħæĥħ
    0.10
    ç®Ĺ
    0.10
    å¤įåıij
    0.10
    ä¼ļå±ķ
    0.10
    åĬłéĩį
    0.10
     recurs
    0.10
    åĬłåī§
    0.09
    Activations Density 0.303%

    No Known Activations