© 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. 19088
    Prev
    Next
    INDEX
    Explanations

    including items or descriptions

    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
    alto
    -0.09
    åķĸ
    -0.08
     Cliff
    -0.08
    Insp
    -0.08
    aising
    -0.08
     Ñĥзн
    -0.08
    INFO
    -0.08
    è´¢
    -0.07
    ARTH
    -0.07
    åı¯è§Ĥ
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJ
    0.10
    ï¼ļ↵
    0.09
    滹
    0.09
    há»ķ
    0.09
    以ä¸ĭåĩłä¸ª
    0.08
    OMEM
    0.08
    çĶŁäº§åĴĮ
    0.08
    éķ°
    0.08
    æĹłæķ°
    0.08
    详ç»ĨçļĦ
    0.08
    Activations Density 0.042%

    No Known Activations