© 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. 61782
    Prev
    Next
    INDEX
    Explanations

    social media sharing

    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
     Lancaster
    -0.08
     ag
    -0.08
    åĪ°å¤Ħ
    -0.08
    æĪ´çĿĢ
    -0.08
    åĽĽå¤Ħ
    -0.08
    榨
    -0.07
     dc
    -0.07
    è¾Ħ
    -0.07
    ako
    -0.07
     form
    -0.07
    POSITIVE LOGITS
    çIJĨ解åĴĮ
    0.12
    æľĿ
    0.11
    _transient
    0.11
    箩
    0.10
    udge
    0.10
    _mirror
    0.10
    uta
    0.10
    berger
    0.10
    è¿Ļåħ¶ä¸Ń
    0.10
    åľ¨æł¡
    0.10
    Activations Density 0.013%

    No Known Activations