© 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. 30095
    Prev
    Next
    INDEX
    Explanations

    SEPULVEDA, Arboleda, Acosta

    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
    çĪµ
    -0.09
    ноÑģÑĤей
    -0.09
    uten
    -0.09
    porter
    -0.09
    tility
    -0.08
    ä»ģ
    -0.08
    çijļ
    -0.08
    urus
    -0.08
    离åİ»
    -0.08
    rese
    -0.08
    POSITIVE LOGITS
    Ø©
    0.16
    a
    0.16
    া
    0.13
    Ûĥ
    0.13
    а
    0.12
    ascript
    0.11
    inha
    0.11
    åŃIJéĩĮ
    0.11
    า
    0.11
    ا
    0.11
    Activations Density 0.606%

    No Known Activations