© 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. 54810
    Prev
    Next
    INDEX
    Explanations

    security forces, personnel, officials, issues

    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
    两次
    -0.10
    被人
    -0.09
    è¥
    -0.09
    åĨįéĢł
    -0.09
    è¶ħåĩº
    -0.08
    èĭ«
    -0.08
    à¸ĩ
    -0.08
    åıijå±ķè§ĦåĪĴ
    -0.08
    _snd
    -0.08
    åѵåĮĸåĻ¨
    -0.08
    POSITIVE LOGITS
    .nih
    0.10
     Lotus
    0.08
     substitution
    0.08
     Jer
    0.08
    örü
    0.08
     CRUD
    0.08
    åĽ´çĿĢ
    0.08
    ä¸įæķ¢
    0.08
    åĮºåĨħ
    0.08
     Disqus
    0.08
    Activations Density 0.015%

    No Known Activations