© 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. 36100
    Prev
    Next
    INDEX
    Explanations

    spouting dialogue

    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
    ality
    -0.12
     Carson
    -0.10
    缤
    -0.10
    æĢĨ
    -0.09
    asl
    -0.09
    ANGLE
    -0.09
    alité
    -0.09
    å¼Ĥ
    -0.08
    çľ·
    -0.08
    angu
    -0.08
    POSITIVE LOGITS
    两åı¥
    0.09
    äºĨä¸Ģéģį
    0.09
    0.09
    ä¸Ģéģį
    0.09
    鸿
    0.09
    ãģªãĤĬ
    0.09
    -ahead
    0.09
     gá»ijc
    0.09
    pter
    0.08
    ILON
    0.08
    Activations Density 0.004%

    No Known Activations