© 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. 34336
    Prev
    Next
    INDEX
    Explanations

    compete or competition

    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
    ties
    -0.12
    éĤ¸
    -0.11
    /or
    -0.10
    å®ŀäºĭ
    -0.10
    bred
    -0.10
    aub
    -0.09
    èĩ¾
    -0.09
    fulness
    -0.09
    ãģĹãģ¾ãģĨ
    -0.08
    åĬŁè¯¾
    -0.08
    POSITIVE LOGITS
    ä¸Ĭå²Ĺ
    0.10
    ILER
    0.10
    unn
    0.10
    obuf
    0.10
    ande
    0.09
    ensation
    0.09
    æ¿ĢçĥĪçļĦ
    0.09
    duit
    0.09
    ingly
    0.09
    licated
    0.09
    Activations Density 0.028%

    No Known Activations