© 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. 62572
    Prev
    Next
    INDEX
    Explanations

    set up or setting

    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
    ç«ŀäºī
    -0.09
    åĬłå¿«åıijå±ķ
    -0.08
    veal
    -0.08
    ãĥĬãĥ³
    -0.08
    æ±°
    -0.08
    å¹ķåIJİ
    -0.08
    lish
    -0.08
    æ°´æºIJ
    -0.08
    nel
    -0.08
    Inlining
    -0.08
    POSITIVE LOGITS
    æIJŃ建
    0.11
    å§Ĭ妹
    0.09
    为人
    0.09
     Parenthood
    0.08
    äºŃ
    0.08
    igram
    0.08
    stead
    0.08
    è½
    0.08
    Built
    0.08
    AYS
    0.08
    Activations Density 0.016%

    No Known Activations