© 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. 34363
    Prev
    Next
    INDEX
    Explanations

    worst-case scenarios and outcomes

    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
    bies
    -0.09
    è°Ĭ
    -0.09
    atrice
    -0.09
    ain
    -0.08
    nant
    -0.08
    _PLATFORM
    -0.08
    Simulation
    -0.08
    è±Ĩ
    -0.08
    üs
    -0.08
    å°ıå·§
    -0.08
    POSITIVE LOGITS
     scenario
    0.17
    scenario
    0.16
    æĥħå½¢
    0.15
    æĥħåĨµä¸ĭ
    0.15
     scenarios
    0.14
    æĥħåĨµ
    0.13
    çļĦæĥħå½¢
    0.13
    çļĦæĥħåĨµ
    0.13
    å±ĢéĿ¢
    0.12
    æĥħæĻ¯
    0.12
    Activations Density 0.028%

    No Known Activations