© 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. 36117
    Prev
    Next
    INDEX
    Explanations

    acting followed by role, career, or position

    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
    æ®ĸ
    -0.10
    åłµ
    -0.09
    æĵĶ
    -0.09
    æĭħå½ĵ
    -0.09
    æĭħä»»
    -0.08
    ä¹IJåĽ¢
    -0.08
    ifier
    -0.08
    ITHER
    -0.08
    代çIJĨåķĨ
    -0.08
    smith
    -0.08
    POSITIVE LOGITS
    ecz
    0.10
    eming
    0.09
    axon
    0.09
    ame
    0.09
    é¢IJ
    0.09
    Interop
    0.09
     einz
    0.09
    èĢħçļĦ
    0.08
    رع
    0.08
    iros
    0.08
    Activations Density 0.006%

    No Known Activations