© 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. 57014
    Prev
    Next
    INDEX
    Explanations

    return or back (movement/destination)

    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
    çī¹æ®ĬæĥħåĨµ
    -0.10
    æļ´éĽ¨
    -0.09
    èĩªåįij
    -0.09
    çļĦä¼Łå¤§
    -0.09
    vat
    -0.09
    èĮ«èĮ«
    -0.08
    说çĿĢ
    -0.08
    umblr
    -0.08
    è¿ľæĻ¯
    -0.08
    eros
    -0.08
    POSITIVE LOGITS
    åĽŀæĿ¥
    0.12
    å½ĴæĿ¥
    0.12
    åĽŀä¾Ĩ
    0.10
    ä¹ĭéĻħ
    0.09
    åĽŀåĽ½
    0.09
    ddy
    0.09
    izen
    0.08
    wen
    0.08
    è·¯è¿ĩ
    0.08
    æĹħç¨ĭ
    0.08
    Activations Density 0.041%

    No Known Activations