© 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. 54868
    Prev
    Next
    INDEX
    Explanations

    false positive

    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
    æºľ
    -0.12
    ev
    -0.09
    æīĵåį°æľº
    -0.09
    ogle
    -0.09
    éĢĭ
    -0.09
    æīĢå±ŀ
    -0.09
    梵
    -0.08
    èļį
    -0.08
    imax
    -0.08
    çĭĻ
    -0.08
    POSITIVE LOGITS
    False
    0.12
    false
    0.11
    èѦ
    0.11
     false
    0.11
    èĻļ
    0.10
    _false
    0.10
     False
    0.10
    æĬ¥èѦ
    0.10
    /false
    0.10
    ä¸įå¿ħè¦ģçļĦ
    0.10
    Activations Density 0.172%

    No Known Activations