© 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. 62294
    Prev
    Next
    INDEX
    Explanations

    buckle your seatbelts

    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
    æݸ
    -0.10
    ä¸Ģéģĵ
    -0.09
    itto
    -0.09
    轺
    -0.09
    stances
    -0.09
    æĸ°æµªè´¢ç»ı
    -0.09
    arem
    -0.09
    CHA
    -0.09
    ase
    -0.08
    .imp
    -0.08
    POSITIVE LOGITS
    æ¸Ń
    0.08
    æłī
    0.08
     Graves
    0.08
    足以
    0.08
     dashes
    0.08
    åķĥ
    0.08
    hart
    0.07
    `t
    0.07
    åĴ¬
    0.07
     اÙĦÙħاضÙĬ
    0.07
    Activations Density 0.215%

    No Known Activations