© 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. 18543
    Prev
    Next
    INDEX
    Explanations

    Orange

    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
    åĴĮåľ°åĮº
    -0.09
    ãģĦãģŁ
    -0.09
    lein
    -0.09
    rier
    -0.09
    омеÑĢ
    -0.09
    ÑĢон
    -0.08
    _WINDOWS
    -0.08
    loe
    -0.08
     اÙĦØŃر
    -0.08
    å°Ĭ严
    -0.08
    POSITIVE LOGITS
    æ±ģ
    0.11
    -yellow
    0.10
    alysis
    0.10
    estate
    0.09
    ÑĮе
    0.09
    /OR
    0.09
    acoes
    0.09
    brains
    0.09
    -red
    0.09
    åīĶ
    0.09
    Activations Density 0.009%

    No Known Activations