© 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. 8312
    Prev
    Next
    INDEX
    Explanations

    Willie, ie, Indie, annie, ester,ector

    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
    ers
    -0.12
    ly
    -0.12
    ively
    -0.12
    ible
    -0.12
    å¿ĥæĦ¿
    -0.11
    sWith
    -0.11
    ments
    -0.11
    ings
    -0.11
    Ùī
    -0.10
    nya
    -0.10
    POSITIVE LOGITS
    ester
    0.11
    ector
    0.11
    hammer
    0.10
    endor
    0.10
    plier
    0.10
    éħĬ
    0.10
    SHOT
    0.10
    obe
    0.10
    psilon
    0.09
    ulong
    0.09
    Activations Density 0.096%

    No Known Activations