© 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. 18292
    Prev
    Next
    INDEX
    Explanations

    state university or college

    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
    è¿Ļéĥ¨åĪĨ
    -0.09
    vil
    -0.09
    eme
    -0.09
    rastructure
    -0.08
    æĸ¯çī¹
    -0.08
    è¿Ļåĩł
    -0.08
    shaw
    -0.08
    ãģįãģ£ãģĭãģij
    -0.08
    inges
    -0.08
    icas
    -0.08
    POSITIVE LOGITS
    oft
    0.09
    geois
    0.09
    ä¸ŃéĢĶ
    0.08
    _SZ
    0.08
    DRV
    0.08
    åħ¨æĸĩ
    0.08
    åIJķ
    0.08
    å¼Ħå¾Ĺ
    0.08
    odor
    0.08
    (Spring
    0.08
    Activations Density 0.008%

    No Known Activations