© 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. 17774
    Prev
    Next
    INDEX
    Explanations

    appropriate / necessary / suitable

    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
    ritis
    -0.10
    éŀĺ
    -0.09
    enal
    -0.09
    æŀ§
    -0.09
    æĶ¾çľ¼
    -0.09
    .vs
    -0.09
     Bol
    -0.08
    isphere
    -0.08
    è·¨åĽ½
    -0.08
     ниÑĩ
    -0.08
    POSITIVE LOGITS
    èļĮ
    0.09
    å®Įæķ´çļĦ
    0.09
    贯彻èIJ½å®ŀ
    0.09
    blast
    0.09
    éŁ³
    0.09
    åĵķ
    0.09
    å²Ķ
    0.09
    éĵĥ
    0.08
    豫
    0.08
     xúc
    0.08
    Activations Density 0.059%

    No Known Activations