© 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. 3817
    Prev
    Next
    INDEX
    Explanations

    payment options or methods

    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
    neys
    -0.10
    åĨĮ
    -0.09
    ä¾Ŀçħ§
    -0.08
    ç´ł
    -0.08
    /copyleft
    -0.08
    cmath
    -0.08
    Ļ¶
    -0.08
    浸
    -0.08
    jay
    -0.08
    å¹Ķ
    -0.08
    POSITIVE LOGITS
    .accept
    0.12
     accept
    0.12
    accept
    0.11
    _accept
    0.11
     accepted
    0.11
    æİ¥åıĹ
    0.11
     Accepted
    0.11
    Accepted
    0.10
    accepted
    0.10
    _accepted
    0.10
    Activations Density 0.032%

    No Known Activations