© 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. 23344
    Prev
    Next
    INDEX
    Explanations

    avoiding negative outcomes

    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
    é¢Ĩè¢ĸ
    -0.11
    ä¸įæĺ¯å¾Ī
    -0.10
    è¿Ļå¥Ĺ
    -0.09
    å¤Ħå¢ĥ
    -0.09
    ä¸įä½ı
    -0.09
    éħ£
    -0.09
    æĭĴä¸į
    -0.09
    çļĦ人çī©
    -0.09
    erb
    -0.09
    è¿Ļæīį
    -0.09
    POSITIVE LOGITS
    åįķçĭ¬
    0.10
    çĽ²çĽ®
    0.09
     bog
    0.09
    ä¸Ģå¼Ģå§ĭå°±
    0.09
    onen
    0.09
    æľīä»»ä½ķ
    0.08
    è´¸
    0.08
    æı¡
    0.08
    째
    0.08
    xFC
    0.08
    Activations Density 0.104%

    No Known Activations