© 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. 35341
    Prev
    Next
    INDEX
    Explanations

    sourcing or sourced from

    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
     Ñģобой
    -0.10
    ilos
    -0.09
    Clark
    -0.09
    ડ
    -0.09
    ISTA
    -0.09
    èĵĿ天
    -0.08
    éľĩæħij
    -0.08
    Tam
    -0.08
     Pent
    -0.08
     MOT
    -0.08
    POSITIVE LOGITS
     from
    0.10
    FromClass
    0.09
    æĢª
    0.09
    å»īä»·
    0.09
    oggle
    0.09
    ç©¿è¿ĩ
    0.09
    Dash
    0.08
     оÑĢг
    0.08
    æĭIJ
    0.08
    era
    0.08
    Activations Density 0.010%

    No Known Activations