© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10063
    Prev
    Next
    INDEX
    Explanations

    extensive background, training, experience, use

    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
    pired
    -0.08
    ä¿ĥæĪIJ
    -0.08
    ÑģÑĤвеннÑĭе
    -0.08
    BIT
    -0.08
    mith
    -0.08
    幸
    -0.08
    å®ŀéĻħæĥħåĨµ
    -0.07
    ian
    -0.07
    æĺī
    -0.07
    UC
    -0.07
    POSITIVE LOGITS
    ignet
    0.11
    igne
    0.10
    gage
    0.10
    çĶļèĩ³æĺ¯
    0.09
     pháºŃn
    0.09
    å¹¿æ³ĽçļĦ
    0.09
    /ext
    0.09
    æĽ²æĬĺ
    0.09
    /native
    0.09
    ç»Ĩèĩ´
    0.09
    Activations Density 0.016%

    No Known Activations