© 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. 61036
    Prev
    Next
    INDEX
    Explanations

    Newcastle

    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
    atical
    -0.12
    ãģĹãģ¾ãģĨ
    -0.10
    æĹĥ
    -0.10
    atically
    -0.10
    est
    -0.10
    аÑĢи
    -0.10
    ware
    -0.09
    éķ³
    -0.09
    西æ¹ĸ
    -0.09
    emas
    -0.09
    POSITIVE LOGITS
    arda
    0.09
     Wife
    0.08
    çĤ³
    0.08
    guess
    0.07
    ä¸Ģé¢Ĺ
    0.07
    åĨ
    0.07
    ª
    0.07
    èĦ¯
    0.07
    OrUpdate
    0.07
    utor
    0.07
    Activations Density 0.004%

    No Known Activations