© 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. 62744
    Prev
    Next
    INDEX
    Explanations

    business merger or proposal

    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
    1
    -0.10
    9
    -0.09
    2
    -0.09
    omens
    -0.09
    3
    -0.09
    è¿Ļ个æĹ¶ä»£
    -0.09
    8
    -0.09
    5
    -0.08
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    èĤ¡ä¸ľå¤§ä¼ļ
    0.14
    æĬķ票
    0.12
    欢è¿İæĤ¨
    0.12
    èĤ¡æĿĥ
    0.11
    CADE
    0.11
    èĤ¡
    0.11
    èĤ¡æĿĥ转让
    0.11
     vot
    0.11
    éĢī举
    0.10
    ÑĤики
    0.10
    Activations Density 0.055%

    No Known Activations