© 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. 62178
    Prev
    Next
    INDEX
    Explanations

    purification or purveyance

    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
    olo
    -0.11
    aber
    -0.10
    поÑĤ
    -0.09
     оÑģобенно
    -0.09
    -gnu
    -0.09
    ingly
    -0.09
    rek
    -0.09
     importantly
    -0.09
    å¿ħä¸įåı¯
    -0.09
    oli
    -0.09
    POSITIVE LOGITS
    POSE
    0.10
    centage
    0.10
    PLE
    0.09
    éĨį
    0.09
    bred
    0.08
    affle
    0.08
    äºĨ大éĩıçļĦ
    0.08
    flix
    0.08
    ries
    0.08
    posed
    0.08
    Activations Density 0.026%

    No Known Activations