© 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. 38722
    Prev
    Next
    INDEX
    Explanations

    state changes

    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
    éĽ³
    -0.11
    ستر
    -0.10
    sey
    -0.09
    antha
    -0.09
    å®ŀè´¨æĢ§
    -0.09
    thest
    -0.09
    shaw
    -0.09
    ÑģÑĤанов
    -0.09
    ief
    -0.09
    ย
    -0.09
    POSITIVE LOGITS
    æĻ°
    0.10
    own
    0.10
    ä»ĸ们æĺ¯
    0.10
    æĦıåĽ¾
    0.10
    asu
    0.10
    agen
    0.09
    kan
    0.09
    å¿ĥæĦı
    0.09
    enant
    0.09
    .nih
    0.09
    Activations Density 0.100%

    No Known Activations