© 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. 6943
    Prev
    Next
    INDEX
    Explanations

    json formatting and parsing

    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
    æĹłå¿§
    -0.10
    æŬ
    -0.09
    udd
    -0.08
    轧
    -0.08
     Lowe
    -0.08
    æĬĬæı¡
    -0.08
    æĭħå½ĵ
    -0.08
     пÑĢим
    -0.08
    izzo
    -0.08
    ä¸ĸ
    -0.08
    POSITIVE LOGITS
    \Json
    0.15
    .JSON
    0.14
    .Json
    0.14
    .JSONException
    0.13
    /json
    0.13
    =json
    0.13
    .Gson
    0.13
    .loads
    0.12
    (Json
    0.12
    .getJSONObject
    0.12
    Activations Density 0.426%

    No Known Activations