© 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. 57083
    Prev
    Next
    INDEX
    Explanations

    understand

    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
    å¥Ķ
    -0.10
    åĵį
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    åºı
    -0.09
     WR
    -0.09
    WR
    -0.08
    åĬŀåѦ
    -0.08
    å¾Ģ
    -0.08
    èĪIJ
    -0.08
    åĬŀäºĭ
    -0.08
    POSITIVE LOGITS
    æĻ¦
    0.18
    çľĭä¸įæĩĤ
    0.18
    èĮ«çĦ¶
    0.13
    è¯Ħè®®
    0.11
    å¤ĸç±į
    0.11
    åĽ«
    0.11
    ä¸įæĩĤ
    0.11
     alien
    0.11
    çIJĨ解
    0.10
    解读
    0.10
    Activations Density 0.120%

    No Known Activations