© 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. 62324
    Prev
    Next
    INDEX
    Explanations

    client relationships

    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
    eds
    -0.11
    thon
    -0.10
    èħ¥
    -0.10
    äºĨä¸Ģä¸ĭ
    -0.10
    ding
    -0.09
    å°ı康
    -0.09
    åŁºè°ĥ
    -0.09
    éĤº
    -0.09
    /from
    -0.09
    INGS
    -0.09
    POSITIVE LOGITS
    èle
    0.15
     sạn
    0.13
    ооÑĢ
    0.11
    ele
    0.11
    rown
    0.10
    innen
    0.09
    家éŨåı£
    0.09
    ç»ıçIJĨ
    0.09
    orts
    0.09
    uren
    0.09
    Activations Density 0.041%

    No Known Activations