© 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. 2693
    Prev
    Next
    INDEX
    Explanations

    attached file

    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
    ,eg
    -0.09
    åĹij
    -0.09
    平稳
    -0.09
    ansk
    -0.09
     Prem
    -0.09
    èľĹ
    -0.09
    èµĬ
    -0.09
    çªĿ
    -0.09
    çīµå¤´
    -0.09
     оÑĤказ
    -0.09
    POSITIVE LOGITS
    éĻĦ件
    0.14
     attached
    0.12
    _attached
    0.11
    attached
    0.11
    íĮĮ
    0.11
    ä¸Ģå°ģ
    0.10
     attaching
    0.10
     kèm
    0.10
     attachment
    0.10
     accompanying
    0.09
    Activations Density 0.104%

    No Known Activations