© 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. 36643
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    æī©
    -0.09
    rog
    -0.09
    EAR
    -0.09
    è¿Ļæł·è¯´
    -0.08
    rollo
    -0.08
    aina
    -0.08
    rap
    -0.08
    resp
    -0.08
    ç½®
    -0.08
    udge
    -0.08
    POSITIVE LOGITS
    é¾Ľ
    0.09
    æµĨ
    0.08
     fen
    0.08
    Ñįн
    0.08
    Guild
    0.08
    GRAM
    0.08
    ANTE
    0.08
    å¤īãĤıãĤĬ
    0.08
    ngr
    0.08
    mia
    0.08
    Activations Density 0.118%

    No Known Activations