© 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. 34242
    Prev
    Next
    INDEX
    Explanations

    describes section

    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
    ðŁı»
    -0.10
    faction
    -0.10
    cation
    -0.10
    ائÙĨ
    -0.09
    åĽŀé¦ĸ
    -0.09
     ÑıвлÑı
    -0.09
    æł·çļĦ
    -0.08
    çĸ¡
    -0.08
    plier
    -0.08
    tings
    -0.08
    POSITIVE LOGITS
    ally
    0.13
    naire
    0.13
    nement
    0.12
    åŁ
    0.11
    otron
    0.11
    aries
    0.11
    ively
    0.10
    ary
    0.10
    isko
    0.10
    naires
    0.09
    Activations Density 0.048%

    No Known Activations