© 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. 31040
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    çĪ·
    -0.09
    unal
    -0.09
    .NewRequest
    -0.09
    ît
    -0.08
     Dodd
    -0.08
    æľīæľŁ
    -0.08
    迤
    -0.08
    gression
    -0.08
    antage
    -0.08
    anz
    -0.08
    POSITIVE LOGITS
     part
    0.16
    éĥ¨åĪĨ
    0.13
     aspect
    0.13
    çļĦéĥ¨åĪĨ
    0.12
    è¿Ļéĥ¨åĪĨ
    0.12
     parts
    0.12
    好çİ©
    0.12
    éĤ£æ®µ
    0.11
    éĥ¨ä»½
    0.11
     aspects
    0.11
    Activations Density 0.084%

    No Known Activations