© 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. 4578
    Prev
    Next
    INDEX
    Explanations

    tablet PCs and computers

    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
    æĿ¯
    -0.12
    luck
    -0.10
    IONS
    -0.09
    ypy
    -0.09
    elli
    -0.09
    lots
    -0.09
    çĶ¨å·¥
    -0.08
    ä¼łæĴŃ
    -0.08
    åĪĿä¸ī
    -0.08
    éħ¬
    -0.08
    POSITIVE LOGITS
    潦
    0.10
    è±Ĩ
    0.10
    ç¬Ķ
    0.09
    读åIJİ
    0.09
    æĶ¯
    0.08
    éĩİ
    0.08
    auses
    0.08
    æ¸łéģĵ
    0.08
    临
    0.08
    审
    0.08
    Activations Density 0.115%

    No Known Activations