© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51094
    Prev
    Next
    INDEX
    Explanations

    showed 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
    enberg
    -0.11
    è¡·
    -0.11
    å¥Ķè·ij
    -0.10
    à¹Į
    -0.10
    orgh
    -0.10
    è¿IJ转
    -0.09
    SharedPtr
    -0.09
    leine
    -0.09
    ommen
    -0.09
    enstein
    -0.09
    POSITIVE LOGITS
    æŀ
    0.09
    ez
    0.09
     appar
    0.09
    OrCreate
    0.08
    OrElse
    0.08
    éķľåŃIJ
    0.08
    aled
    0.08
    lication
    0.08
     Mot
    0.07
    è·¸
    0.07
    Activations Density 0.007%

    No Known Activations