© 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. 1083
    Prev
    Next
    INDEX
    Explanations

    structure and format

    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
     crow
    -0.11
    hots
    -0.09
    ERM
    -0.09
    erty
    -0.08
    lemen
    -0.08
    razy
    -0.08
    kek
    -0.08
    elyn
    -0.08
    andes
    -0.08
    crow
    -0.08
    POSITIVE LOGITS
     structure
    0.13
    ç»ĵæŀĦ
    0.12
    æŀ¶æŀĦ
    0.12
    structure
    0.11
     Structure
    0.10
    çµIJæ§ĭ
    0.10
     STRUCT
    0.10
     format
    0.10
    æł¼å¼ı
    0.10
    /format
    0.10
    Activations Density 0.093%

    No Known Activations