© 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. 4731
    Prev
    Next
    INDEX
    Explanations

    closing html/js syntax

    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
    æ¥Ķ
    -0.09
    大å®Ĺ
    -0.09
    åĿĹ
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    hits
    -0.08
    ÑĥÑĪки
    -0.08
    产æĿĥ
    -0.08
    äºĴè¡¥
    -0.07
    è¯Ŀ说
    -0.07
     pac
    -0.07
    POSITIVE LOGITS
    åķľ
    0.10
    ÑĤÑĢо
    0.09
    _GR
    0.08
     XK
    0.08
    ÑģоÑĢ
    0.08
    rupted
    0.08
    éĻIJãĤĬ
    0.08
    å¥ī
    0.08
    dish
    0.08
    pees
    0.08
    Activations Density 0.013%

    No Known Activations