© 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. 63566
    Prev
    Next
    INDEX
    Explanations

    pros and cons

    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
    _PW
    -0.10
    è´¯
    -0.09
    INU
    -0.09
    åī¯å±Ģéķ¿
    -0.09
    imax
    -0.08
    SPORT
    -0.08
    Ñĥз
    -0.08
    SPA
    -0.08
    osl
    -0.08
    ina
    -0.08
    POSITIVE LOGITS
    ÑĤе
    0.10
    éĩįéĩį
    0.09
    åŁĶ
    0.09
    åĬ²
    0.09
    å¾Īå¤ļæľĭåıĭ
    0.09
    commons
    0.08
    istan
    0.08
    ä¼ļåijĺ
    0.08
    人éĢł
    0.08
    ted
    0.08
    Activations Density 0.011%

    No Known Activations