© 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. 32689
    Prev
    Next
    INDEX
    Explanations

    seat belts

    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
    목
    -0.11
    åģıåIJij
    -0.09
    害ç¾ŀ
    -0.09
     dial
    -0.09
     dispatch
    -0.09
    fee
    -0.09
    shadow
    -0.08
    è°ĥ度
    -0.08
    åĵ¥ä»¬
    -0.08
    åĨ³å®ļ
    -0.08
    POSITIVE LOGITS
    æŃ¢
    0.11
    åı¸
    0.11
     Seat
    0.10
     seat
    0.10
    seat
    0.09
    æijĶåĢĴ
    0.09
    座æ¤ħ
    0.09
    _seat
    0.09
    åħľ
    0.09
    åłij
    0.09
    Activations Density 0.070%

    No Known Activations