© 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. 49893
    Prev
    Next
    INDEX
    Explanations

    thoughts and observations

    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
    æºľ
    -0.11
    ä½ľåĵģåĨħ容
    -0.10
    å²ij
    -0.09
    忽
    -0.09
    orian
    -0.09
     OSI
    -0.09
    ify
    -0.08
     congr
    -0.08
    åįģéĩĮ
    -0.08
    è¹ĩ
    -0.08
    POSITIVE LOGITS
     thoughts
    0.18
     Thoughts
    0.17
    å¿ĥå¾Ĺ
    0.15
    ç¬Ķè®°
    0.15
    çļĦæĥ³æ³ķ
    0.14
    æĦŁæĤŁ
    0.13
    æĢĿ绪
    0.13
    æĢĿèĢĥ
    0.12
    念头
    0.12
    æĥ³æ³ķ
    0.12
    Activations Density 0.088%

    No Known Activations