© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6967
    Prev
    Next
    INDEX
    Explanations

    fast or faster

    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
    hip
    -0.11
    ãģ¹ãģį
    -0.11
    isor
    -0.10
    zelf
    -0.09
    ette
    -0.09
    ÑĪка
    -0.09
    oret
    -0.09
    auge
    -0.09
    naire
    -0.09
    大佬
    -0.08
    POSITIVE LOGITS
    idious
    0.23
    -paced
    0.14
     mẽ
    0.13
    /small
    0.12
    ëģĶ
    0.11
    ðŁı»
    0.11
    -growing
    0.11
    acre
    0.11
    ness
    0.11
     chóng
    0.11
    Activations Density 0.024%

    No Known Activations