© 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. 62032
    Prev
    Next
    INDEX
    Explanations

    Django or javadoc

    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
    è¯Ĩ
    -0.08
    occo
    -0.08
    为代表
    -0.08
    ***
    -0.08
    _RGBA
    -0.07
    ime
    -0.07
     cry
    -0.07
     Cry
    -0.07
     lan
    -0.07
    çĤĴ
    -0.07
    POSITIVE LOGITS
    åĨ·åĨ·
    0.12
    驽
    0.10
    æĶ»åĬ¿
    0.09
    ç¥ľ
    0.09
    èĢĮéĿŀ
    0.09
    è¿ľè¿ľ
    0.09
    éģĴ
    0.09
    èĢĮä¸įæĺ¯
    0.09
    æĹ¥è®¯
    0.09
    çŁ¥éģĵäºĨ
    0.09
    Activations Density 0.077%

    No Known Activations