© 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. 27115
    Prev
    Next
    INDEX
    Explanations

    matters to you

    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
    -0.09
    ilight
    -0.08
    强æľīåĬĽ
    -0.08
     niên
    -0.08
    strup
    -0.08
    趣åij³
    -0.08
    ibold
    -0.08
    an
    -0.08
    ift
    -0.08
    adal
    -0.07
    POSITIVE LOGITS
    fully
    0.12
    lessly
    0.10
    åĺ´
    0.10
    ful
    0.09
    åĪĿåĪĽ
    0.09
    less
    0.09
    æ²®
    0.09
    nell
    0.09
    åĺ´åĶĩ
    0.09
    äºİæѤ
    0.09
    Activations Density 0.009%

    No Known Activations