© 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. 58382
    Prev
    Next
    INDEX
    Explanations

    language names and origins

    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
    åºŁ
    -0.09
    è¶Ĭ
    -0.08
    éĵĽ
    -0.08
     Pitt
    -0.08
    ament
    -0.08
    ering
    -0.08
    opia
    -0.08
     Humanities
    -0.08
    rep
    -0.08
     rep
    -0.08
    POSITIVE LOGITS
    -speaking
    0.12
    -language
    0.11
    éĻ¬
    0.10
    _ptrs
    0.10
    unya
    0.09
    è¨Ģ
    0.09
    è¯ļå®ŀ
    0.09
    çĪª
    0.09
    éĢĨ转
    0.09
    佬
    0.09
    Activations Density 0.098%

    No Known Activations