© 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. 35485
    Prev
    Next
    INDEX
    Explanations

    planning and policy documents

    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
    è¿Ļéĥ¨åĪĨ
    -0.10
    主æĿĥ
    -0.09
    exampleInput
    -0.09
    sie
    -0.08
    ืà¸Ń
    -0.08
    è¿ĺæľīä»Ģä¹Ī
    -0.08
    .encoding
    -0.08
    ographics
    -0.08
    aben
    -0.08
    reta
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.10
     Muss
    0.10
    ä¾
    0.09
    зÑĭ
    0.09
    åĴĮ个人
    0.09
    æĻºåĬĽ
    0.09
    _rw
    0.09
    éĦĤ
    0.08
    wright
    0.08
    ä¸įæĸŃåıijå±ķ
    0.08
    Activations Density 0.016%

    No Known Activations