© 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. 10272
    Prev
    Next
    INDEX
    Explanations

    TEDX, PET CT, Initiative

    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
    ä¸Ģæľ¬
    -0.10
    омеÑĢ
    -0.08
    æ®·
    -0.08
     reck
    -0.08
     ISBN
    -0.08
    ament
    -0.08
     Mitt
    -0.08
    ãģ®ãģĬ
    -0.08
    ä¾ĽéĶĢ
    -0.08
    åħ±åĴĮ
    -0.08
    POSITIVE LOGITS
     Blanch
    0.10
    _FALL
    0.09
    ishly
    0.09
    ä¸ĩåı°
    0.09
     вÑģего
    0.09
    ä¸Ĭåīį
    0.08
    .ps
    0.08
    ENTITY
    0.08
    æķ´æķ´
    0.08
    æĽ´ä½ķåĨµ
    0.08
    Activations Density 0.007%

    No Known Activations