© 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. 50778
    Prev
    Next
    INDEX
    Explanations

    risky behaviors and risk-taking

    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
    èĽĬ
    -0.10
    侮辱
    -0.10
    å¯ĤéĿĻ
    -0.09
    éĿ¢åŃIJ
    -0.09
    é¼ĵèĪŀ
    -0.09
    æķħ乡
    -0.09
    TOR
    -0.09
    éĵ·
    -0.09
    inged
    -0.09
    ppe
    -0.08
    POSITIVE LOGITS
    è¡Į为
    0.32
     behavior
    0.31
    è¡ĮçĤº
    0.26
     behaviors
    0.24
     Behavior
    0.23
     behaviour
    0.23
    çļĦè¡Į为
    0.21
    behavior
    0.21
     behaviours
    0.19
    _behavior
    0.19
    Activations Density 0.157%

    No Known Activations