© 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. 39723
    Prev
    Next
    INDEX
    Explanations

    harsh conditions or climate

    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
     Fletcher
    -0.09
    人大
    -0.09
     mond
    -0.08
    mers
    -0.08
    害æĢķ
    -0.08
    zeit
    -0.08
    Ĩ
    -0.08
    æĸ°å±ĢéĿ¢
    -0.08
    isu
    -0.08
     Meer
    -0.08
    POSITIVE LOGITS
    ness
    0.16
    ened
    0.16
    ening
    0.15
    æĹłæ¯Ķ
    0.13
    bour
    0.11
    NESS
    0.11
    vard
    0.11
    ly
    0.11
    éħ½
    0.10
    eres
    0.10
    Activations Density 0.004%

    No Known Activations