© 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. 57080
    Prev
    Next
    INDEX
    Explanations

    guidelines reveal

    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
    dry
    -0.09
    æ´²
    -0.08
    æĪIJç«ĭ
    -0.08
    è¥Ł
    -0.08
     dry
    -0.08
    çī§åľº
    -0.08
    æĵĴ
    -0.08
    å°ĸ
    -0.07
    asso
    -0.07
    ä¹¾
    -0.07
    POSITIVE LOGITS
    é«ĺçŃīæķĻèĤ²
    0.11
    æĶ¿åĬ¡
    0.09
    çĽijå¯Ł
    0.09
    æĶ¿åºľ
    0.09
    æĶ¿åºľéĩĩè´Ń
    0.09
    æĪijçĪ±ä½ł
    0.09
     Crown
    0.09
    åľ¨åħ¨åĽ½
    0.09
    overnment
    0.08
    å«ĸ
    0.08
    Activations Density 0.241%

    No Known Activations