© 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. 61117
    Prev
    Next
    INDEX
    Explanations

    software initals and names

    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
    gether
    -0.15
    Ø·ÙĬع
    -0.09
    eer
    -0.09
    lator
    -0.09
    bidden
    -0.08
    ToObject
    -0.08
    itis
    -0.08
    eof
    -0.08
    eq
    -0.08
    ment
    -0.08
    POSITIVE LOGITS
    Ùij
    0.17
    åīįæīĢ
    0.15
    s
    0.09
    zioni
    0.09
    çħ
    0.09
    ť
    0.09
    强æľīåĬĽ
    0.09
    à¹
    0.08
    -être
    0.08
    atters
    0.08
    Activations Density 1.045%

    No Known Activations