© 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. 34855
    Prev
    Next
    INDEX
    Explanations

    out-of

    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
    empre
    -0.10
    å½ķçĶ¨
    -0.10
    éĵİ
    -0.09
    æĪ¢
    -0.09
    onn
    -0.09
    Lint
    -0.09
    èĦĨ
    -0.09
    æıĨ
    -0.09
    gems
    -0.09
    èıĬ
    -0.09
    POSITIVE LOGITS
    erb
    0.10
    /out
    0.09
    source
    0.09
    -out
    0.09
    comes
    0.09
     Out
    0.09
    iza
    0.08
    ersed
    0.08
    orado
    0.08
    take
    0.08
    Activations Density 0.038%

    No Known Activations