© 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. 49324
    Prev
    Next
    INDEX
    Explanations

    cell and molecule related terms

    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
    sheets
    -0.10
    s
    -0.10
    sense
    -0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    misc
    -0.09
    samples
    -0.09
    soc
    -0.09
    ãģĦãģĨ
    -0.09
    heet
    -0.09
     ones
    -0.09
    POSITIVE LOGITS
    sWith
    0.18
    swith
    0.17
    sto
    0.16
    sthrough
    0.14
    (s
    0.13
    ÂŃs
    0.12
    [s
    0.11
    ss
    0.11
    们
    0.11
    so
    0.11
    Activations Density 1.011%

    No Known Activations