© 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. 39424
    Prev
    Next
    INDEX
    Explanations

    hail and hailing from

    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
    okie
    -0.09
    éºĿ
    -0.09
    ERGE
    -0.09
    ylvania
    -0.09
    ality
    -0.08
     mÃŃ
    -0.08
     Dame
    -0.08
    èĢģçĪ·
    -0.08
    æĸ°åŁİ
    -0.08
    æĥĨ
    -0.08
    POSITIVE LOGITS
    stones
    0.13
    stone
    0.11
    atory
    0.10
    ä¸Ģ声
    0.09
    storm
    0.09
    pole
    0.09
    åij±
    0.09
    pery
    0.09
    LING
    0.09
    itudes
    0.08
    Activations Density 0.007%

    No Known Activations