© 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. 28051
    Prev
    Next
    INDEX
    Explanations

    your local area

    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
    éĶ´
    -0.09
    亹
    -0.09
     dise
    -0.09
    ma
    -0.09
    åıĪ好
    -0.08
    _toolbar
    -0.08
    qli
    -0.08
    airo
    -0.08
    ibo
    -0.08
    pis
    -0.08
    POSITIVE LOGITS
    å½ĵåľ°çļĦ
    0.20
     local
    0.19
    åľ°åĮºçļĦ
    0.19
    æīĢåľ¨åľ°
    0.18
    å½ĵåľ°
    0.18
    åľ°åĮº
    0.18
    éĻĦè¿ij
    0.17
    æľ¬åľ°
    0.17
    æīĢåľ¨
    0.17
    éĻĦè¿ijçļĦ
    0.16
    Activations Density 0.105%

    No Known Activations