© 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. 18495
    Prev
    Next
    INDEX
    Explanations

    prototype and prototyping

    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
    anel
    -0.10
    ä¸įè§ģ
    -0.09
    å½Ĵ纳
    -0.08
    åĿļ强
    -0.08
     wig
    -0.08
    åĬ¨éĿĻ
    -0.08
    Sql
    -0.08
    æ¦Ĥæĭ¬
    -0.07
    setData
    -0.07
    xmax
    -0.07
    POSITIVE LOGITS
    prototype
    0.13
     prototypes
    0.13
     prototype
    0.13
     Prototype
    0.12
    æ½¢
    0.12
    åİŁåŀĭ
    0.12
    Prototype
    0.11
    èįī
    0.11
    quisite
    0.10
    çīĪæľ¬
    0.10
    Activations Density 0.104%

    No Known Activations