© 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. 17698
    Prev
    Next
    INDEX
    Explanations

    ranges between

    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
    ä¸ĭåįĬåľº
    -0.10
    æĹģè¾¹
    -0.10
    ä»Ħ
    -0.10
    åįĵ
    -0.09
    åıijçİ°èĩªå·±
    -0.09
    èµĮ
    -0.09
    å°ıé¾Ļ
    -0.09
    udit
    -0.09
    ç½Ķ
    -0.09
    é¾Į
    -0.09
    POSITIVE LOGITS
    为æŃ¢
    0.11
    0
    0.10
    8
    0.09
    5
    0.09
    9
    0.09
    enson
    0.09
    3
    0.09
    1
    0.08
    6
    0.08
    7
    0.08
    Activations Density 0.114%

    No Known Activations