© 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. 49469
    Prev
    Next
    INDEX
    Explanations

    accompanying / accompanies

    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
    Hands
    -0.09
     lick
    -0.09
    æīĭä¸ŃçļĦ
    -0.09
    ä»Ŀ
    -0.09
    jing
    -0.09
    insk
    -0.09
    _gid
    -0.08
    SSI
    -0.08
    owi
    -0.08
     Hands
    -0.08
    POSITIVE LOGITS
    åħħæĸ¥
    0.11
    称ä¹ĭ
    0.10
    åįłæį®äºĨ
    0.10
    çĻ»åľº
    0.10
    åıĸ代
    0.10
    岿
    0.10
    åħ¥åľº
    0.09
    çĤ¹ç¼Ģ
    0.09
    ä¾Ħ
    0.09
    æĪijåĽ½
    0.09
    Activations Density 0.235%

    No Known Activations