© 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. 10512
    Prev
    Next
    INDEX
    Explanations

    quantity adjectives

    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
     dps
    -0.09
    çĻ¾
    -0.08
     ÑĥÑĩиÑĤÑĭва
    -0.08
    å¼Ľ
    -0.08
    ÑĥÑħ
    -0.08
    mentor
    -0.08
    ç®Ĺæĺ¯
    -0.08
     Noir
    -0.08
    ForObject
    -0.08
    du
    -0.08
    POSITIVE LOGITS
    åķĨæľº
    0.10
    鬻
    0.09
    ç¥ī
    0.09
    izu
    0.09
    æīĵåħ¥
    0.09
    æĮ¡
    0.08
    俪
    0.08
    off
    0.08
    çİĭæľĿ
    0.08
    INFO
    0.08
    Activations Density 0.062%

    No Known Activations