© 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. 57172
    Prev
    Next
    INDEX
    Explanations

    service and quality

    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
    asics
    -0.09
    environment
    -0.09
     dys
    -0.08
    éĻįèIJ½
    -0.08
    æijĦåħ¥
    -0.08
    è¯¥æł¡
    -0.08
    CEE
    -0.08
    .digest
    -0.08
    鸡
    -0.08
    æ¿Ĵ
    -0.08
    POSITIVE LOGITS
     coverage
    0.15
    Coverage
    0.12
    coverage
    0.11
     Coverage
    0.11
    _coverage
    0.10
    æĬĢæľ¯æĶ¯æĮģ
    0.10
     поÑģл
    0.09
     обÑģлÑĥж
    0.09
    çĶŁæ¶¯
    0.09
    okus
    0.09
    Activations Density 0.132%

    No Known Activations