© 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. 22425
    Prev
    Next
    INDEX
    Explanations

    names following "and"

    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
    åĸĦæĦı
    -0.11
    ierge
    -0.11
    ç¼ł
    -0.10
    éĢĨè¡Į
    -0.10
    å¥Ķ
    -0.09
    edy
    -0.09
    ilar
    -0.09
    ellen
    -0.09
    éĻħ
    -0.09
    /thumb
    -0.09
    POSITIVE LOGITS
    ãģ§ãģĬ
    0.10
    ä¸Ģåı°
    0.09
    .define
    0.09
    ä¸ĢæĶ¯
    0.08
    ä¿ĿåĪ©
    0.08
    POL
    0.08
     pil
    0.08
    ina
    0.08
     pol
    0.08
     POL
    0.08
    Activations Density 0.164%

    No Known Activations