© 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. 1951
    Prev
    Next
    INDEX
    Explanations

    set up

    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
    åĩŃ
    -0.09
    çĸĥ
    -0.09
    符
    -0.09
    toJson
    -0.09
    ä¸įçĦ¶
    -0.09
     пÑĢедоÑģÑĤавлен
    -0.08
    å·¥ä½ľæĬ¥åijĬ
    -0.08
    èĩ§
    -0.08
    çŃ¾åŃĹ
    -0.08
    åĮºåĨħ
    -0.08
    POSITIVE LOGITS
    çĤĬ
    0.08
     thresholds
    0.08
    .setUp
    0.08
    æĹĭ
    0.08
    éĹ¨æ§Ľ
    0.08
     sail
    0.08
    _xlim
    0.08
    è¿IJ转
    0.08
     Sphinx
    0.08
    éģĤ
    0.08
    Activations Density 0.026%

    No Known Activations