© 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. 30274
    Prev
    Next
    INDEX
    Explanations

    information please

    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
    åľī
    -0.09
     Able
    -0.09
     francais
    -0.08
    éĿ¢åĮħ
    -0.08
     Dame
    -0.08
    _devices
    -0.08
    éĿ¢ç²ī
    -0.08
    ién
    -0.08
     Libert
    -0.08
    -ahead
    -0.08
    POSITIVE LOGITS
    请大家
    0.09
    çĪ¸
    0.09
    .TAG
    0.09
    logen
    0.09
    æľīè¿Ļæł·çļĦ
    0.08
    Forg
    0.08
    æĹłä¸į
    0.08
    wall
    0.08
    egan
    0.08
    SO
    0.08
    Activations Density 0.008%

    No Known Activations