© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20321
    Prev
    Next
    INDEX
    Explanations

    This Blog

    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
    éĻ¬
    -0.10
    bler
    -0.10
    mun
    -0.09
    çĤ¹æ»´
    -0.08
     confront
    -0.08
    callbacks
    -0.08
    atische
    -0.08
     crib
    -0.08
     Marian
    -0.08
    ervations
    -0.08
    POSITIVE LOGITS
    (Search
    0.14
    æIJľç´¢
    0.14
    (search
    0.14
     search
    0.13
    =search
    0.13
    /search
    0.13
    .Search
    0.13
    .search
    0.13
    /Search
    0.13
    ðŁĶį
    0.13
    Activations Density 0.181%

    No Known Activations