© 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. 62262
    Prev
    Next
    INDEX
    Explanations

    concert tour

    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
    -0.17
    zelf
    -0.10
    amax
    -0.10
    ril
    -0.09
    endra
    -0.09
    å¹´ç»Ī
    -0.09
    etter
    -0.08
    rac
    -0.08
    hood
    -0.08
    ðŁı»
    -0.08
    POSITIVE LOGITS
    ior
    0.11
    ivals
    0.09
    oug
    0.09
    eki
    0.09
    icut
    0.09
    çĮ¿
    0.09
     cú
    0.09
    ãģ¾ãģķ
    0.09
    aptcha
    0.08
    aky
    0.08
    Activations Density 0.005%

    No Known Activations