© 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. 54265
    Prev
    Next
    INDEX
    Explanations

    squeeze, squeegee

    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
    aceous
    -0.16
    ivation
    -0.08
    most
    -0.08
    å¾®éĩı
    -0.08
    rea
    -0.08
    rop
    -0.08
    ivers
    -0.08
    arus
    -0.08
    son
    -0.08
    quil
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    utow
    0.10
    ably
    0.09
    Ø«ÙĦ
    0.09
    ernet
    0.09
    plorer
    0.09
    ãģĵãģ¨
    0.09
    dw
    0.09
    å²ĺ
    0.09
    errat
    0.09
    Activations Density 0.005%

    No Known Activations