© 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. 23373
    Prev
    Next
    INDEX
    Explanations

    comments and replies

    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
    ä¹İ
    -0.11
    loom
    -0.10
    mente
    -0.10
    hel
    -0.09
    ulkan
    -0.09
    oft
    -0.09
    ctic
    -0.09
    çļĦæĥħæĦŁ
    -0.09
     Ree
    -0.09
    ç²¹
    -0.09
    POSITIVE LOGITS
    edom
    0.09
     ÐĶм
    0.09
    豨
    0.09
    ìĤ¬íķŃ
    0.09
    aires
    0.09
    ç½ijåıĭè¯Ħ论
    0.08
    âľį
    0.08
    è¾ħ
    0.08
    ãĤĭãĤĪãģĨãģ«
    0.08
    dsl
    0.08
    Activations Density 0.020%

    No Known Activations