© 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. 62682
    Prev
    Next
    INDEX
    Explanations

    lack of ability or understanding

    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
    æĥ³ä¸įåĪ°
    -0.10
    å¸®ä½ł
    -0.10
     Dude
    -0.09
    mos
    -0.09
    ä¾Ķ
    -0.09
     BSP
    -0.09
    对æīĭ
    -0.08
    gan
    -0.08
     porta
    -0.08
    缣
    -0.08
    POSITIVE LOGITS
    ä½ĨæĪij
    0.10
    æĥŃ
    0.10
    éĿ©
    0.10
    åıįçľģ
    0.10
    æ»ĭ
    0.09
    avel
    0.09
    ä¿Ŀå§Ĩ
    0.09
    纸ä¸Ĭ
    0.09
    çĶ°éĩİ
    0.09
    è¾ľ
    0.09
    Activations Density 0.121%

    No Known Activations