© 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. 39652
    Prev
    Next
    INDEX
    Explanations

    percentage of votes

    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
     наÑģÑĤоÑı
    -0.10
    次ä¼ļè®®
    -0.10
    åľ¨æѤä¹ĭåīį
    -0.09
    å®ŀäºĭæ±Ĥæĺ¯
    -0.09
    LIMIT
    -0.09
    åħ®
    -0.09
    交éĻħ
    -0.09
    éĻ¤éĿŀ
    -0.09
    èij³
    -0.08
    é¼ĵèĪŀ
    -0.08
    POSITIVE LOGITS
     toJSON
    0.09
    以ä¸ĬçļĦ
    0.09
    ngen
    0.09
    Kal
    0.08
    orges
    0.08
     acknowledgement
    0.08
     Choice
    0.08
    è½°
    0.08
     Kal
    0.08
     Dunk
    0.08
    Activations Density 0.022%

    No Known Activations