© 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. 17071
    Prev
    Next
    INDEX
    Explanations

    decorate and lights

    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
    æĬĹçĶŁç´ł
    -0.09
    çĬģ
    -0.09
    åħ¥çĿ¡
    -0.08
    è´¨åľ°
    -0.08
    顽强
    -0.08
    åĿļå®ŀçļĦ
    -0.08
    æıį
    -0.08
    åģ¥åº·çļĦ
    -0.08
     burn
    -0.08
    opa
    -0.08
    POSITIVE LOGITS
    è£ħ饰
    0.14
    å¸ĥç½®
    0.11
     lights
    0.11
    èĶĵ
    0.11
    çģ¯ç¬¼
    0.11
     decorations
    0.10
    è£ħæī®
    0.10
    å¨ĺ
    0.10
    饰
    0.10
    elan
    0.09
    Activations Density 0.185%

    No Known Activations