© 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. 19066
    Prev
    Next
    INDEX
    Explanations

    appetite, consumption, aversion

    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
    çĴĥ
    -0.09
    èį¡
    -0.09
     banned
    -0.09
    è¯ŀ
    -0.09
    UPS
    -0.08
    imar
    -0.08
    æĢ¥åī§
    -0.08
    jen
    -0.08
    ç¦ģ
    -0.08
    æĶ¾æĺł
    -0.08
    POSITIVE LOGITS
    åİĮ
    0.11
    åħ¥åı£
    0.10
    åĭī强
    0.10
    åŁĭ
    0.09
    iginal
    0.09
    åİŃ
    0.08
    otto
    0.08
    æµ£
    0.08
    ä½į
    0.08
    éĿ¢çĻ½
    0.08
    Activations Density 0.034%

    No Known Activations