© 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. 21555
    Prev
    Next
    INDEX
    Explanations

    license, attribution, and copyright

    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
    尤为
    -0.09
    aras
    -0.09
    çIJħ
    -0.09
    _TBL
    -0.08
    amel
    -0.08
    è¿ħ
    -0.08
    åĢŁåı£
    -0.08
    onaut
    -0.08
    çĸı导
    -0.08
    leanup
    -0.08
    POSITIVE LOGITS
    èѦ
    0.10
    åĨľå®¶ä¹IJ
    0.10
    تÙħ
    0.09
    为æѤ
    0.08
    å°¸
    0.08
    olon
    0.08
    ä¸įåĬ¨
    0.08
    à¸ģลาà¸ĩ
    0.07
    æķ°æį®ä¸Ńå¿ĥ
    0.07
    ä»Ĺ
    0.07
    Activations Density 0.085%

    No Known Activations