© 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. 30746
    Prev
    Next
    INDEX
    Explanations

    photos

    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
    eer
    -0.11
    ãĤ·ãĥ§ãĥ³
    -0.09
    åĽŀäºĭ
    -0.09
    onym
    -0.08
    æįİ
    -0.08
    eur
    -0.08
     tale
    -0.08
    omain
    -0.08
    iola
    -0.08
    TRS
    -0.08
    POSITIVE LOGITS
    hoot
    0.14
    ynthesis
    0.09
    cob
    0.09
    绩
    0.08
    嵬
    0.08
    OfDay
    0.08
    èĥ½æ»¡è¶³
    0.08
    æħĿ
    0.08
    оÑĤ
    0.08
    .POS
    0.08
    Activations Density 0.030%

    No Known Activations