© 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. 49974
    Prev
    Next
    INDEX
    Explanations

    Key West, books, computers, emoji

    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
    ovsky
    -0.10
     Hind
    -0.10
    OrUpdate
    -0.10
    å¹ħ
    -0.09
    омеÑĢ
    -0.09
    rez
    -0.09
    ç¤Ļ
    -0.09
    rtl
    -0.09
    arbonate
    -0.09
    åĵªæĢķæĺ¯
    -0.09
    POSITIVE LOGITS
    akk
    0.08
    å»Ľ
    0.08
    å¼łå®¶
    0.08
    äºĨ好åĩł
    0.08
    iod
    0.08
    нима
    0.08
    山顶
    0.08
    azon
    0.08
     Vect
    0.08
     outgoing
    0.08
    Activations Density 0.008%

    No Known Activations