© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35809
    Prev
    Next
    INDEX
    Explanations

    school children

    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
    è¿ĩå¾Ģ
    -0.10
     sẵ
    -0.10
    flix
    -0.10
    èµ°å¾Ĺ
    -0.09
    èĨı
    -0.09
    ç½ijå°ıç¼ĸ
    -0.09
    被æīĵ
    -0.09
    esser
    -0.09
     Oaks
    -0.09
     Rath
    -0.09
    POSITIVE LOGITS
    ç½¢äºĨ
    0.08
    ÑĢÑĥд
    0.08
    lee
    0.08
    림
    0.08
     domest
    0.08
     Abram
    0.08
    gee
    0.08
    ç¨ļ
    0.08
    alien
    0.07
    åĪĽéĢłæĢ§
    0.07
    Activations Density 0.034%

    No Known Activations