© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7827
    Prev
    Next
    INDEX
    Explanations

    aid, support, defense, kit, first aid

    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
     Leo
    -0.09
    aram
    -0.09
     Perr
    -0.08
    å½ĵä¹ĭ
    -0.08
    Tools
    -0.08
    迤
    -0.08
    ham
    -0.07
    æĴŀ
    -0.07
     ham
    -0.07
     agenda
    -0.07
    POSITIVE LOGITS
    iative
    0.11
    odus
    0.10
    ạng
    0.09
    _receiver
    0.09
    indr
    0.08
     (~(
    0.08
    æľªçŁ¥
    0.08
    maal
    0.08
    ingroup
    0.08
    avenport
    0.08
    Activations Density 0.006%

    No Known Activations