© 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. 32155
    Prev
    Next
    INDEX
    Explanations

    leaf descriptions

    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
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    -0.10
    duit
    -0.09
    骧
    -0.09
    á»ī
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
     dame
    -0.09
    çĶŁç´ł
    -0.09
    iska
    -0.08
    ities
    -0.08
     лиÑĪÑĮ
    -0.08
    POSITIVE LOGITS
    ãģ£ãģ±
    0.13
    iness
    0.10
    ../
    0.10
    y
    0.10
    èĵģ
    0.10
    walker
    0.09
    ä½ķåĨµ
    0.09
    lets
    0.09
    ÑĮев
    0.09
    finding
    0.09
    Activations Density 0.025%

    No Known Activations