© 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. 32354
    Prev
    Next
    INDEX
    Explanations

    Muammer G. Bilgi Brothers

    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
    ç°ĩ
    -0.10
    s
    -0.09
    éĨĮ
    -0.09
    æĨ§
    -0.08
    éĥħ
    -0.08
    áĥĹ
    -0.08
    ouis
    -0.08
    åĵºä¹³
    -0.08
    fen
    -0.08
    åħ¼èģĮ
    -0.08
    POSITIVE LOGITS
    ValuePair
    0.09
    venta
    0.09
    嵬
    0.09
    èĶļ
    0.09
    CustomLabel
    0.08
    奸
    0.08
    deo
    0.08
    irl
    0.08
    åı¤èĢģçļĦ
    0.08
    รวà¸Ķ
    0.08
    Activations Density 0.008%

    No Known Activations