© 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. 6506
    Prev
    Next
    INDEX
    Explanations

    casualty and casual wear

    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
    æĭĹ
    -0.11
    ç´§è·Ł
    -0.10
    å°ıå°ıçļĦ
    -0.10
     Nob
    -0.10
    æĿijåħļæĶ¯éĥ¨
    -0.09
    Ñĥнк
    -0.09
    ä¸Ģ个好çļĦ
    -0.09
    /posts
    -0.09
    aceous
    -0.09
    à¸Ħà¸Ńย
    -0.09
    POSITIVE LOGITS
    ities
    0.13
    mente
    0.11
    itas
    0.11
    ties
    0.10
    dehyde
    0.10
     minded
    0.10
    ware
    0.10
    s
    0.09
    ly
    0.09
    ités
    0.09
    Activations Density 0.008%

    No Known Activations