© 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. 23281
    Prev
    Next
    INDEX
    Explanations

    per unit, per dollar, per pill

    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
    èĩ¼
    -0.10
    åıĮåıĮ
    -0.10
    ä¸į解
    -0.09
    æºĥ
    -0.09
    èĬŁ
    -0.09
    éĴ½
    -0.09
    åıįä¹ĭ
    -0.09
    éĩĬ
    -0.09
     tá»ī
    -0.09
    èĽ¸
    -0.09
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.09
    indle
    0.08
    engage
    0.08
     Khan
    0.08
    æīĵäºĨ
    0.08
    shake
    0.08
    reira
    0.08
    ipp
    0.08
     ÑģамоÑģÑĤоÑı
    0.08
    åł´
    0.07
    Activations Density 0.003%

    No Known Activations