© 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. 18079
    Prev
    Next
    INDEX
    Explanations

    receive and hand over

    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
    å¼ĢèįĴ
    -0.10
    leases
    -0.10
    ายà¸Ļ
    -0.09
    家å±ħ
    -0.09
    渣
    -0.09
    æ¾į
    -0.09
    çģ¶
    -0.08
    æ¶ī足
    -0.08
    hton
    -0.08
    ç»ŀ
    -0.08
    POSITIVE LOGITS
    éĢĴç»Ļ
    0.18
    交ç»Ļ
    0.16
     handing
    0.14
    亲æīĭ
    0.14
    éĢĴ
    0.14
    æĭ¿åĩºæĿ¥
    0.13
    éĢģè¾¾
    0.13
    æĶ¶åĽŀ
    0.13
     handed
    0.13
    ä¿Ŀ管
    0.13
    Activations Density 0.097%

    No Known Activations