© 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. 53796
    Prev
    Next
    INDEX
    Explanations

    such a/that

    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¿©
    -0.10
     ìķĦ주
    -0.10
    REA
    -0.09
    æı¿
    -0.09
    屿
    -0.09
    è¿Ļä¹Īä¹ħ
    -0.09
    rik
    -0.09
    æĢ§å¼º
    -0.08
    기ìĹIJ
    -0.08
    åıĻ
    -0.08
    POSITIVE LOGITS
    mate
    0.10
    æѤç§į
    0.10
    oner
    0.10
    lla
    0.09
    ult
    0.09
    羣çIJĨ
    0.09
    éĩįå·¥
    0.09
     дела
    0.09
    aks
    0.09
     ÑģовеÑĢÑĪен
    0.09
    Activations Density 0.043%

    No Known Activations