© 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. 57234
    Prev
    Next
    INDEX
    Explanations

    specific tools

    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
     HÆ°Æ¡ng
    -0.09
    æijĬ
    -0.08
    _sha
    -0.07
    ä¸İåħ¶
    -0.07
    inherits
    -0.07
    ä¸įäºĨ
    -0.07
    èµĦæºIJéħįç½®
    -0.07
    ãģ¨ãģ¨ãĤĤãģ«
    -0.07
     qa
    -0.07
     ì§
    -0.07
    POSITIVE LOGITS
    çŃī
    0.12
    çŃīè¡Įä¸ļ
    0.11
    è¿Ļç±»
    0.11
    ä¹ĭç±»
    0.11
     etc
    0.11
    çŃīåIJĦç§į
    0.10
    çŃīå½¢å¼ı
    0.10
    ãģªãģ©
    0.10
    çŃīåĬŁèĥ½
    0.10
    çŃīä¸Ģæī¹
    0.09
    Activations Density 0.377%

    No Known Activations