© 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. 18364
    Prev
    Next
    INDEX
    Explanations

    official titles

    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
    mö
    -0.08
     Kimber
    -0.08
     Dub
    -0.08
    anst
    -0.08
    å®Į
    -0.07
     lane
    -0.07
    æĵį
    -0.07
    @brief
    -0.07
    bast
    -0.07
    IVO
    -0.07
    POSITIVE LOGITS
    ä¹ĭäºī
    0.12
    ç¨Ĺ
    0.10
    对åħ¶è¿Ľè¡Į
    0.10
    移åĬ¨ç«¯
    0.09
    Ñĥй
    0.09
    å·¥ä½ľä½ľé£İ
    0.09
    åĢĻéĢī
    0.09
    æī§è¡ĮåĬĽ
    0.09
    人éĢī
    0.09
    èįīåĿª
    0.09
    Activations Density 0.012%

    No Known Activations