© 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. 30767
    Prev
    Next
    INDEX
    Explanations

    users of things

    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
    åħ¶æīĢ
    -0.11
     Mods
    -0.09
    amu
    -0.09
    åĥı个
    -0.09
    ong
    -0.08
    -Agent
    -0.08
    ongs
    -0.08
    åı°æ¹¾
    -0.08
     infl
    -0.08
    .charCodeAt
    -0.08
    POSITIVE LOGITS
    使çĶ¨èĢħ
    0.17
    èĢħ
    0.14
    åıĤä¸İèĢħ
    0.14
    使çĶ¨èĢħæĪĸ
    0.12
    主ä¹īèĢħ
    0.12
    èĢħãģ¯
    0.11
     users
    0.11
    çĶ¨æĪ·
    0.11
    çĶ¨æĪ·æıIJä¾Ľ
    0.11
    ä»İä¸ļèĢħ
    0.10
    Activations Density 0.274%

    No Known Activations