© 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. 30614
    Prev
    Next
    INDEX
    Explanations

    like to verb

    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
    åĨįä¹Ł
    -0.10
    æĬµæĮ¡
    -0.10
    åıĪæĺ¯
    -0.10
    à¸Ħà¸Ńย
    -0.10
    深交
    -0.09
    ãģªãģĬ
    -0.09
    ä¸įåĨį
    -0.09
    ä»įçĦ¶
    -0.09
    ä»įçĦ¶æĺ¯
    -0.09
    .CG
    -0.09
    POSITIVE LOGITS
     imb
    0.09
    ead
    0.09
    å¤ļå¤ļ
    0.08
    èŀ³
    0.08
    ayed
    0.08
    åѤ
    0.08
    çĻ½çĻ½
    0.08
     cap
    0.08
     ìłķëıĦ
    0.08
    èī¯æĢ§
    0.07
    Activations Density 0.017%

    No Known Activations