© 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. 35130
    Prev
    Next
    INDEX
    Explanations

    Agency for Cancer Research

    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
    æ³½
    -0.11
    æģ½
    -0.09
    ertas
    -0.09
    麻
    -0.09
    éĢIJ
    -0.09
     frost
    -0.09
    澤
    -0.09
     Pruitt
    -0.09
    ä¸ĵåijĺ
    -0.09
    outed
    -0.09
    POSITIVE LOGITS
    èĩ´çĻĮ
    0.15
    æıĸ
    0.10
    ÑģÑĤавка
    0.09
    Risk
    0.09
     Risk
    0.09
    Ki
    0.09
    NOP
    0.09
    æĬĹçĻĮ
    0.08
    (Expected
    0.08
    risk
    0.08
    Activations Density 0.645%

    No Known Activations