© 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. 30682
    Prev
    Next
    INDEX
    Explanations

    minecraft, Spitzer, world

    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
    åİķ
    -0.09
    ItemSelected
    -0.09
    诱
    -0.09
    eny
    -0.09
    xa
    -0.09
    aben
    -0.08
    ilee
    -0.08
    棻
    -0.08
    æĶ¹åĪ¶
    -0.08
    èģĮ
    -0.08
    POSITIVE LOGITS
    èĥĮæĻ¯
    0.10
    æľĿçĿĢ
    0.09
    ulls
    0.09
    åĬĽæ°Ķ
    0.09
    amina
    0.09
    riz
    0.09
    åĬĽéĩı
    0.09
    端æŃ£
    0.08
    utz
    0.08
    å²Ĺ
    0.08
    Activations Density 0.002%

    No Known Activations