© 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. 3225
    Prev
    Next
    INDEX
    Explanations

    importance politically

    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
    å¤ļå°ijéĴ±
    -0.09
    -minus
    -0.09
    åĽ´çĿĢ
    -0.09
    èĬ±èįī
    -0.08
    otten
    -0.08
    éķ¿å®ī
    -0.08
    稷
    -0.08
    æŁIJç§į
    -0.08
    otas
    -0.08
    åľĪ
    -0.08
    POSITIVE LOGITS
    ÑĬ
    0.10
    urtle
    0.09
    çĪ±ç¾İ
    0.09
     kh
    0.08
    绣çŃ¹æİ¨è¿Ľ
    0.08
     pard
    0.08
    çĵ¶
    0.08
    èݪ
    0.08
    infeld
    0.08
    DIC
    0.08
    Activations Density 0.065%

    No Known Activations