© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37946
    Prev
    Next
    INDEX
    Explanations

    Murphy's people and places

    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
    åŃIJéĩĮ
    -0.11
    íĮIJ
    -0.10
    _WM
    -0.09
    éĶ¢
    -0.09
    ä¹İ
    -0.09
    shore
    -0.09
    íĴĪ
    -0.08
     dÃłng
    -0.08
    owed
    -0.08
    helm
    -0.08
    POSITIVE LOGITS
    teenth
    0.11
    ../../../
    0.10
    ãģĹãĤĩãģĨ
    0.10
    unk
    0.09
    æ±ģ
    0.09
    NotAllowed
    0.09
    atively
    0.08
    teen
    0.08
    edia
    0.08
    aper
    0.08
    Activations Density 0.012%

    No Known Activations