© 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. 17902
    Prev
    Next
    INDEX
    Explanations

    input and what follows

    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
    omas
    -0.09
    andro
    -0.09
    enso
    -0.09
    hind
    -0.09
    åĿĢ
    -0.09
    éĻIJãĤĬ
    -0.09
    öff
    -0.09
    ambre
    -0.09
    æŀģéĻIJ
    -0.08
    avian
    -0.08
    POSITIVE LOGITS
    ters
    0.11
    è¿ĽæĿ¥
    0.10
    prising
    0.09
    æľŃ
    0.09
    MethodManager
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    /output
    0.09
    uted
    0.09
    itial
    0.09
    æŃĩ
    0.09
    Activations Density 0.021%

    No Known Activations