© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53184
    Prev
    Next
    INDEX
    Explanations

    pronouns and articles

    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
    ANNER
    -0.10
    ìłģìľ¼ë¡ľ
    -0.09
    ì´ī
    -0.09
    aders
    -0.08
    esModule
    -0.08
    gettext
    -0.08
    åĮħ
    -0.08
    è¿Ļæł·è¯´
    -0.08
    æ´İ
    -0.08
    atures
    -0.08
    POSITIVE LOGITS
    åħ¬ç½ijå®īå¤ĩ
    0.09
    éºĵ
    0.08
    fin
    0.08
    ibil
    0.08
     paz
    0.08
    è¢į
    0.08
    สรร
    0.08
    éĺŁåıĭ
    0.08
    æ´¥
    0.08
    ovi
    0.07
    Activations Density 0.160%

    No Known Activations