© 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. 21755
    Prev
    Next
    INDEX
    Explanations

    ligament

    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
    teen
    -0.09
    ãģıãĤĮ
    -0.09
    ¡°
    -0.09
    顺
    -0.08
    Unnamed
    -0.08
    rd
    -0.08
    fit
    -0.08
    ren
    -0.08
    ru
    -0.08
    OfType
    -0.08
    POSITIVE LOGITS
    y
    0.11
    eur
    0.11
    vine
    0.10
    涯
    0.10
    ibri
    0.10
    -level
    0.10
    lems
    0.09
    ingly
    0.09
     unlikely
    0.09
    æĸ°éĹ»åıijå¸ĥ
    0.09
    Activations Density 0.003%

    No Known Activations