© 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. 18008
    Prev
    Next
    INDEX
    Explanations

    representation or representations

    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
    oug
    -0.10
     Retro
    -0.09
    为äºĨéģ¿åħį
    -0.09
    oud
    -0.09
    ä¼ĹæīĢ
    -0.08
    ä¸įæħİ
    -0.08
    gars
    -0.08
    åºł
    -0.08
    assin
    -0.08
    ìŀ¥ìĿĦ
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.12
    representation
    0.11
    æīĭæ³ķ
    0.10
     representation
    0.10
    åĩºæĿ¥
    0.09
    AGING
    0.09
    太æŀģ
    0.09
    æ¸ħæ¥ļ
    0.09
     representations
    0.09
    å±ķçİ°åĩº
    0.09
    Activations Density 0.062%

    No Known Activations