© 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. 49696
    Prev
    Next
    INDEX
    Explanations

    buildup and deposits

    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
    åĪĨè¡Į
    -0.10
    æī§æĦı
    -0.10
    æºħ
    -0.09
     chứ
    -0.09
    ĥģ
    -0.09
     Cunning
    -0.09
    FilterWhere
    -0.09
    (AF
    -0.09
    麻
    -0.09
    rica
    -0.09
    POSITIVE LOGITS
    æĪij没æľī
    0.10
    åĽ´ç»ķ
    0.09
     on
    0.09
    æѧ
    0.09
     Sno
    0.08
    çĦī
    0.08
    ihan
    0.08
    é©·
    0.08
    庸
    0.08
    åĽŀé¦ĸ
    0.08
    Activations Density 0.090%

    No Known Activations