© 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. 35253
    Prev
    Next
    INDEX
    Explanations

    hair treatments and conditioning

    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
    è´§æŀ¶
    -0.09
    ÑĤика
    -0.09
    kip
    -0.09
    urt
    -0.09
    íĴĪ
    -0.08
    ç½ijç»ľä¼łæĴŃ
    -0.08
    endo
    -0.08
    pret
    -0.08
    OTS
    -0.08
    ors
    -0.08
    POSITIVE LOGITS
    ç´łè´¨
    0.11
    åĪ¶åĵģ
    0.10
     Rudd
    0.10
    жи
    0.09
    æ§İ
    0.09
    åĬŁå¤«
    0.09
    è´¨éĩıåĴĮ
    0.09
    ÑĢод
    0.09
    wheel
    0.09
    .SIG
    0.09
    Activations Density 0.011%

    No Known Activations