© 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. 34881
    Prev
    Next
    INDEX
    Explanations

    in the process

    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
    èĪ¬
    -0.09
    nut
    -0.08
     enr
    -0.08
    ä¸įèµ·
    -0.08
    è¿Ļä¸įæĺ¯
    -0.08
    gio
    -0.08
    诱
    -0.08
    ÑıÑī
    -0.07
    o
    -0.07
    gor
    -0.07
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭä¸Ń
    0.11
    积累äºĨ
    0.11
     dabei
    0.10
    åijľ
    0.09
    å¼Ħ
    0.09
    æºħ
    0.09
    çļĦåIJĮæŶ
    0.09
    éĵ¸
    0.09
    èµ¢å¾ĹäºĨ
    0.09
    åĻ«
    0.09
    Activations Density 0.040%

    No Known Activations