© 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. 53513
    Prev
    Next
    INDEX
    Explanations

    Ferrari, Ferris, Ferrer

    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
    etic
    -0.09
    ethe
    -0.09
    hood
    -0.09
    ç¼Ĺ
    -0.09
    æݸ
    -0.09
    yh
    -0.09
    asca
    -0.09
    orton
    -0.09
    sic
    -0.09
    etics
    -0.08
    POSITIVE LOGITS
    ÙħÙĬÙĨ
    0.10
    ãĤī
    0.10
    è§ij
    0.10
    èĨº
    0.10
    éħIJ
    0.09
    ìĻķ
    0.09
    ities
    0.09
    áng
    0.09
     dù
    0.09
    eros
    0.09
    Activations Density 0.025%

    No Known Activations