© 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. 62287
    Prev
    Next
    INDEX
    Explanations

    Nexus.Client

    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
    anova
    -0.10
    åĿIJä¸ĭ
    -0.09
    .present
    -0.09
    央
    -0.08
    dsl
    -0.08
    éĻIJ
    -0.08
    ç½Ĥ
    -0.08
     pres
    -0.08
    FIT
    -0.08
    oze
    -0.08
    POSITIVE LOGITS
    éħį
    0.10
     оÑĢи
    0.10
    _forum
    0.09
    Wiki
    0.09
    论åĿĽ
    0.09
    éĺ´éĺ³
    0.09
    俨
    0.09
    wiki
    0.09
    å®ĺæĸ¹
    0.09
     اÙĦبÙĨ
    0.09
    Activations Density 0.138%

    No Known Activations