© 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. 2296
    Prev
    Next
    INDEX
    Explanations

    era, segregation, wall, action

    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
    éĽĢ
    -0.10
    æķij人
    -0.10
    çĶ¸
    -0.09
    éĴŀ
    -0.09
    æ´½
    -0.09
    澶
    -0.09
    ãģıãĤĬ
    -0.09
    åĩºè·¯
    -0.09
    éĮ¢
    -0.09
    ç²¾
    -0.09
    POSITIVE LOGITS
    éĻĭ
    0.10
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    pit
    0.08
    aud
    0.08
    _COMPAT
    0.08
     casts
    0.08
    åĪ¶åº¦
    0.08
    -era
    0.08
    -com
    0.08
    æĹ¶ä»£çļĦ
    0.08
    Activations Density 0.022%

    No Known Activations