© 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. 5083
    Prev
    Next
    INDEX
    Explanations

    essential oil or lavender

    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
    iled
    -0.09
    æĽľ
    -0.09
    heimer
    -0.09
    黳
    -0.09
    社交åªĴä½ĵ
    -0.09
     Nut
    -0.08
    auge
    -0.08
    lets
    -0.08
    ert
    -0.08
    aug
    -0.08
    POSITIVE LOGITS
    KeyType
    0.10
    精油
    0.10
    iskey
    0.10
    é«ĺåĩº
    0.09
    åĬłåĢį
    0.09
    ä¹ĭå¤ľ
    0.09
    mos
    0.08
    èĦijåŃIJ
    0.08
    绣
    0.08
    æŃ¤æ¬¡
    0.08
    Activations Density 0.014%

    No Known Activations