© 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. 27872
    Prev
    Next
    INDEX
    Explanations

    at followed by space or other words

    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
    ìį¨
    -0.09
    æĴ¤
    -0.09
    æ¢
    -0.08
    è°¯
    -0.08
    èĩªæѤ
    -0.08
    èĸ¤
    -0.08
    åĨįåĪ°
    -0.08
     dialogRef
    -0.08
    onian
    -0.08
     Sav
    -0.08
    POSITIVE LOGITS
    åĴ©
    0.09
    æĮ¯ãĤĬ
    0.09
    åıijå±ķéĺ¶æ®µ
    0.09
    墨
    0.09
    æĽĻ
    0.08
    åıijè¨Ģ人
    0.08
     rents
    0.08
    _ble
    0.08
    æ·¡åĮĸ
    0.08
    æĮ¤åİĭ
    0.08
    Activations Density 0.140%

    No Known Activations