© 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. 20043
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    åIJĮä¸ļ
    -0.11
    éļħ
    -0.10
    å°Ĩèĩªå·±çļĦ
    -0.09
    ç«ŀäºī对æīĭ
    -0.09
    å§IJ
    -0.09
    æĻ°
    -0.09
    éĤĢ
    -0.09
    åįħ
    -0.09
    _FRONT
    -0.08
    该åİ¿
    -0.08
    POSITIVE LOGITS
    èµĺ
    0.09
    laden
    0.09
    åľ¨å®¶éĩĮ
    0.08
    åľ¨å®¶
    0.08
    uffer
    0.08
    Ctl
    0.08
    BED
    0.08
    åľ¨åºĬä¸Ĭ
    0.07
    tap
    0.07
    ÑģÑĤв
    0.07
    Activations Density 0.196%

    No Known Activations