© 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. 5754
    Prev
    Next
    INDEX
    Explanations

    definition of term

    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
    اÙĬ
    -0.10
    ä¸Ģå®ļç¨ĭ度
    -0.10
    ropa
    -0.10
    oming
    -0.09
    åīĶ
    -0.09
    常å§Ķ
    -0.09
    ì±ħ
    -0.09
    lä
    -0.09
    anas
    -0.09
    ging
    -0.09
    POSITIVE LOGITS
    perature
    0.20
    inals
    0.19
    olecular
    0.15
    ä¸įæ¸ħ
    0.11
     ÑģлÑĥжбÑĭ
    0.11
    lessly
    0.11
    ament
    0.11
    ite
    0.11
    inal
    0.09
    èĨ³
    0.09
    Activations Density 0.085%

    No Known Activations