© 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. 29913
    Prev
    Next
    INDEX
    Explanations

    Ruby language context

    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
    sWith
    -0.13
    asan
    -0.09
    ather
    -0.09
    thal
    -0.09
    æľīèī²éĩijå±ŀ
    -0.08
    .addObject
    -0.08
    ingly
    -0.08
    ss
    -0.08
    éķIJ
    -0.08
    rier
    -0.08
    POSITIVE LOGITS
    æµĨ
    0.10
    iaz
    0.09
    plate
    0.09
    Ùħا
    0.09
     Ð
    0.09
    ¶
    0.09
    posable
    0.08
    dap
    0.08
     иÑģÑĤ
    0.08
    inate
    0.08
    Activations Density 0.026%

    No Known Activations