© 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. 30216
    Prev
    Next
    INDEX
    Explanations

    causes me

    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
    çĪ±äºº
    -0.08
    åįĴ
    -0.08
    aret
    -0.08
    åijĬåĪ«
    -0.08
    çľĭçĿĢ
    -0.08
    åĤ¬
    -0.07
    æ²¾
    -0.07
    åĶ§
    -0.07
    éħĿ
    -0.07
     luggage
    -0.07
    POSITIVE LOGITS
    ingly
    0.13
    å½ĵåľ°æĶ¿åºľ
    0.13
    æĪijåĢij
    0.12
    ä»»ä½ķ人
    0.12
    人们
    0.11
    ä¸įå°ij人
    0.11
    å½ĵæŶçļĦ
    0.11
    éľı
    0.11
    æĪij们
    0.10
    大家åĪĨ享
    0.10
    Activations Density 0.040%

    No Known Activations