© 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. 50047
    Prev
    Next
    INDEX
    Explanations

    three Pure Ones

    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
    ÑīÑĥ
    -0.09
    åIJĮèĥŀ
    -0.08
     Ty
    -0.08
    ç½®
    -0.08
    溢
    -0.08
     tutor
    -0.08
    çIJ®
    -0.08
    èĪ«
    -0.08
    utura
    -0.08
    åºı
    -0.08
    POSITIVE LOGITS
    è¯ģçĽij
    0.10
    é£ŀè¡Į
    0.10
    èĻ¹æ¡¥
    0.10
    สà¸ĸ
    0.10
    ç»ĻäºĪ
    0.09
    å¾ij
    0.09
    åĮĸ身
    0.09
    å·¡éĢ»
    0.09
    éĢģæĿ¥
    0.09
    給äºĪ
    0.09
    Activations Density 0.071%

    No Known Activations