© 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. 23817
    Prev
    Next
    INDEX
    Explanations

    questions starting with how, what, can, do

    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
    信念
    -0.09
    æ¯ķç«Ł
    -0.09
    好äºĨ
    -0.09
    ä¹Łä¸įè¦ģ
    -0.08
    å°±åı¯ä»¥äºĨ
    -0.08
    éĥ¨åī¯
    -0.08
    åĪ«è¯´
    -0.08
    raham
    -0.08
    ç¡ķ
    -0.08
    å°±ç®Ĺæĺ¯
    -0.08
    POSITIVE LOGITS
    对åħ¶
    0.11
    åĽłèĢĮ
    0.11
    åĽłæѤ
    0.11
    对åħ¶è¿Ľè¡Į
    0.11
    æįħ
    0.10
     therefore
    0.10
     поÑįÑĤомÑĥ
    0.10
    è¸Ĭ
    0.10
    对æѤ
    0.09
     wiÄĻc
    0.09
    Activations Density 0.494%

    No Known Activations