© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20530
    Prev
    Next
    INDEX
    Explanations

    Ferguson and Ferdinand

    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
    -même
    -0.10
    æµľ
    -0.09
    à¤ĺ
    -0.08
    ÑįÑĢ
    -0.08
    幡
    -0.08
    verted
    -0.08
    åĩ«
    -0.08
    ãģĹãģ¾ãģĨ
    -0.08
    unan
    -0.08
    æľ¬ç½ij
    -0.08
    POSITIVE LOGITS
    naire
    0.12
    ingly
    0.11
    ments
    0.10
    åĽŀäºĭ
    0.09
     Trafford
    0.09
    ÑĨа
    0.09
    naires
    0.09
    ned
    0.09
    esus
    0.09
    nable
    0.09
    Activations Density 0.002%

    No Known Activations