© 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. 19313
    Prev
    Next
    INDEX
    Explanations

    compound names

    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
    æ°´æµģ
    -0.09
    zo
    -0.09
    åı¯æĮģç»Ń
    -0.09
     Soda
    -0.09
    mdat
    -0.09
     Boyd
    -0.08
    ustain
    -0.08
    åIJ¯ç¤º
    -0.08
    NoSuch
    -0.08
    åŃIJå¼¹
    -0.08
    POSITIVE LOGITS
    人æķ°
    0.09
    atile
    0.09
    Ñģлов
    0.09
    éŀŃ
    0.09
    renom
    0.09
    çĬģ
    0.09
    éĻĽ
    0.09
    æĴ
    0.09
    åĮºåŁŁæĢ§
    0.09
    èĽ°
    0.08
    Activations Density 0.011%

    No Known Activations