© 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. 34354
    Prev
    Next
    INDEX
    Explanations

    director, movie, tv series, film

    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
    stin
    -0.10
    _movies
    -0.09
    undry
    -0.09
    تاÙĨ
    -0.09
    天空
    -0.09
     trunk
    -0.09
    onto
    -0.09
    äºĨ好
    -0.09
    :checked
    -0.09
    bsp
    -0.09
    POSITIVE LOGITS
    æĬ±
    0.09
    æķ²
    0.08
    èĴ¯
    0.08
    迳
    0.08
    æĬ±çĿĢ
    0.08
     Kl
    0.08
    æĻ¯
    0.08
     hold
    0.08
    çĬĬ
    0.08
    ales
    0.08
    Activations Density 0.171%

    No Known Activations