© 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. 2759
    Prev
    Next
    INDEX
    Explanations

    promise

    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
    å±ķå¼Ģ
    -0.09
    ä¸İåIJ¦
    -0.08
    æĸŁ
    -0.08
    æıŃå¼Ģ
    -0.08
    åıįåºĶ
    -0.08
    otp
    -0.07
     Pres
    -0.07
    slug
    -0.07
    åį°è±¡
    -0.07
    ivet
    -0.07
    POSITIVE LOGITS
     promises
    0.21
    æī¿è¯º
    0.18
     promised
    0.16
     promise
    0.15
    诱
    0.14
    诱æĥij
    0.14
    åIJ¸å¼ķåĬĽ
    0.13
     promising
    0.12
    åIJ¸å¼ķ
    0.12
    promise
    0.12
    Activations Density 0.051%

    No Known Activations