© 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. 38720
    Prev
    Next
    INDEX
    Explanations

    leverage, power, terms, outcome

    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
    èĩĥ
    -0.09
    ÙĬع
    -0.09
    гÑĢан
    -0.09
     proximity
    -0.08
    å¿Ĵ
    -0.08
    .mdl
    -0.08
    ordin
    -0.08
    _constant
    -0.08
    edly
    -0.08
    浩
    -0.08
    POSITIVE LOGITS
    è°ĪåĪ¤
    0.13
    åºķæ°Ķ
    0.12
     поÑıви
    0.11
    çŃ¹çłģ
    0.11
    çłĿ
    0.10
    åľ°ä½į
    0.09
     bargaining
    0.09
    åijĽ
    0.09
    åĪĨåĮĸ
    0.09
     leverage
    0.09
    Activations Density 0.020%

    No Known Activations