© 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. 2158
    Prev
    Next
    INDEX
    Explanations

    widget properties

    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
    andes
    -0.10
    ãģ£ãģįãĤĬ
    -0.09
    éªĭ
    -0.09
    pollo
    -0.09
     bbw
    -0.09
     piping
    -0.09
    rw
    -0.09
    ложений
    -0.09
    aign
    -0.09
    -going
    -0.09
    POSITIVE LOGITS
    gle
    0.09
    ering
    0.09
    ãģ¾ãĤĮ
    0.09
    ling
    0.08
    æĺİåªļ
    0.08
    urd
    0.08
    ometry
    0.08
    abo
    0.08
    ä¹ĭä¸ĭ
    0.08
    icious
    0.08
    Activations Density 0.016%

    No Known Activations