© 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. 30636
    Prev
    Next
    INDEX
    Explanations

    being [something]

    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
    izable
    -0.09
    -tabs
    -0.09
    ableObject
    -0.08
    Flying
    -0.08
    DidLoad
    -0.08
    æĮĤçĿĢ
    -0.08
    н
    -0.08
    ä¸ĩåĪĨ
    -0.08
    订éĺħ
    -0.08
    æŁ¥æĺİ
    -0.08
    POSITIVE LOGITS
    踹
    0.10
    空åīį
    0.09
    ä¹¾åĿ¤
    0.09
    å¾ĹæĦı
    0.09
    iy
    0.09
    sey
    0.09
    eva
    0.09
    Boy
    0.08
    SHOT
    0.08
     ÑģовеÑĢÑĪен
    0.08
    Activations Density 0.073%

    No Known Activations