© 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. 27226
    Prev
    Next
    INDEX
    Explanations

    subject to

    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
    .netbeans
    -0.09
    åĪĴ
    -0.09
    åıįèĢĮ
    -0.09
    çIJĨæĥ³çļĦ
    -0.08
    ä¿¡æģ¯æľįåĬ¡
    -0.08
     Äijấu
    -0.08
    åĿĹ
    -0.08
    DET
    -0.08
    è¦ģéĹ»
    -0.08
    REE
    -0.08
    POSITIVE LOGITS
    subjects
    0.11
    ç±³å°Ķ
    0.10
    çijŀ
    0.09
    å¤Ł
    0.09
    ï¸ı
    0.09
     subjects
    0.09
    åĮł
    0.09
    lug
    0.09
    аÑĢам
    0.09
    (subject
    0.09
    Activations Density 0.013%

    No Known Activations