© 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. 62790
    Prev
    Next
    INDEX
    Explanations

    on-base percentage

    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
    è§ģè¯ģ
    -0.09
    éĴľ
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
     IPC
    -0.08
    ially
    -0.08
    ì¸
    -0.08
    off
    -0.08
    OFF
    -0.08
    icot
    -0.08
    çĶ¨æ°´
    -0.07
    POSITIVE LOGITS
    åĢ¼
    0.09
    ä¸įéĮ¯
    0.09
    åħ±åĴĮ
    0.09
    oland
    0.09
    åįĹéĥ¨
    0.09
    _PREF
    0.09
    åŀĽ
    0.09
    _dispatch
    0.09
    grave
    0.08
    aye
    0.08
    Activations Density 0.005%

    No Known Activations