© 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. 33813
    Prev
    Next
    INDEX
    Explanations

    lifting objects

    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
    leigh
    -0.09
    alf
    -0.09
    rou
    -0.09
    ´
    -0.08
    ر
    -0.08
    åģ»
    -0.08
    æĢĿãģĦ
    -0.08
     liking
    -0.08
    erate
    -0.08
    ald
    -0.08
    POSITIVE LOGITS
    ãĤ¢ãĥĥãĥĹ
    0.10
    mates
    0.10
    tings
    0.10
    ï¸
    0.10
    aurant
    0.09
    AndServe
    0.09
    eden
    0.09
    ors
    0.09
    scoped
    0.09
    urse
    0.09
    Activations Density 0.021%

    No Known Activations