© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23942
    Prev
    Next
    INDEX
    Explanations

    go ahead and

    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
    rawl
    -0.09
    slots
    -0.08
    éºĴ
    -0.08
    ãģıãĤĬ
    -0.08
    coil
    -0.08
    å§ĭ建
    -0.08
    Senior
    -0.08
    auce
    -0.08
    apel
    -0.08
    æĥij
    -0.08
    POSITIVE LOGITS
    èĢĨ
    0.09
    å®īåİ¿
    0.09
    lug
    0.09
    edly
    0.09
    eft
    0.09
     Ñģами
    0.08
    好äºĭ
    0.08
    å¨Ł
    0.08
    itt
    0.08
    INA
    0.08
    Activations Density 0.004%

    No Known Activations