© 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. 54154
    Prev
    Next
    INDEX
    Explanations

    small caps

    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
    oooooooo
    -0.08
    代表æĢ§
    -0.08
    sWith
    -0.08
    ä¸Ĭå®ĺ
    -0.08
    ä¾ĭå¤ĸ
    -0.07
    /all
    -0.07
    .Designer
    -0.07
    çĶį
    -0.07
    í
    -0.07
    åıįèħIJåĢ¡å»ī
    -0.07
    POSITIVE LOGITS
    ä¼ģä¸ļæıIJä¾Ľ
    0.11
    çĿģ
    0.10
    åijĽ
    0.09
     rocked
    0.09
    arb
    0.09
    å°ıç¼ĸä¸Ģèµ·
    0.09
    æĪijåľ¨
    0.09
    æµģæ·Į
    0.09
    opup
    0.08
     Compound
    0.08
    Activations Density 0.143%

    No Known Activations