© 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. 39915
    Prev
    Next
    INDEX
    Explanations

    divided into

    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
    ä½
    -0.11
     вÑĭбÑĢ
    -0.09
    2
    -0.09
    åı¤äºº
    -0.09
    urge
    -0.09
     ÑįнеÑĢги
    -0.08
    _INC
    -0.08
    6
    -0.08
    ä¸įèµ·
    -0.08
    çĥ¹
    -0.08
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.13
     коÑĤоÑĢаÑı
    0.10
    主è¦ģæľī
    0.09
    é¦ĸåħĪæĺ¯
    0.09
    å°±å¦ĤåIJĮ
    0.09
    åĪĨ为
    0.09
    èģŀãģį
    0.09
     ones
    0.09
    快讯
    0.09
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.09
    Activations Density 0.357%

    No Known Activations