© 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. 55248
    Prev
    Next
    INDEX
    Explanations

    name changes or identifiers

    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
     Roths
    -0.12
    çĥŁ
    -0.09
    rieg
    -0.09
    èµĿ
    -0.09
    æĨ¶
    -0.09
    ä¸ĢèĤ¡
    -0.09
    ä¸Ģåı¥è¯Ŀ
    -0.09
    缨
    -0.09
    erties
    -0.09
    thur
    -0.09
    POSITIVE LOGITS
    为åĩĨ
    0.09
    Dou
    0.08
    å§ĵåIJį
    0.08
    èģļä¼ļ
    0.08
     пеÑĢевод
    0.08
    icles
    0.08
    æĭ¿æĿ¥
    0.08
     каÑĤал
    0.08
     whom
    0.08
    åħĪçĶŁ
    0.08
    Activations Density 0.029%

    No Known Activations