© 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. 27458
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    reon
    -0.09
    >Last
    -0.09
    åįĬ个
    -0.09
    âľª
    -0.09
    ÑĢог
    -0.09
    æ³½
    -0.09
    ÙĬÙĦ
    -0.09
    è°Ĵ
    -0.09
    ensation
    -0.09
    oyo
    -0.09
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.09
    综åIJĪç´łè´¨
    0.09
    (always
    0.08
     Rede
    0.08
    vc
    0.07
    ãĤĤãģĦãģĦ
    0.07
    ä»İ容
    0.07
    fty
    0.07
    åħįçĸ«åĬĽ
    0.07
    ä¸Ģç»ı
    0.07
    Activations Density 0.469%

    No Known Activations