© 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. 58757
    Prev
    Next
    INDEX
    Explanations

    essential or necessary things

    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
    ular
    -0.09
     Dry
    -0.08
    å½»
    -0.08
    Dry
    -0.08
    æĶ¶çĽĬ
    -0.08
    .Ordinal
    -0.08
    eut
    -0.08
     comb
    -0.08
    å¹¼ç¨ļ
    -0.08
    å¥ļ
    -0.08
    POSITIVE LOGITS
    ä¸įåı¯æĪĸ缺
    0.20
    å¿ħä¸įåı¯å°ij
    0.19
    ä¸įåı¯ç¼ºå°ij
    0.19
    å¿ħå¤ĩ
    0.18
    å¿ħéľĢ
    0.18
    å¿ħä¸įåı¯
    0.15
    å¿ħè¦ģ
    0.15
     necessity
    0.15
    å¿ħè¦ģçļĦ
    0.14
     необÑħодим
    0.14
    Activations Density 0.127%

    No Known Activations