© 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. 39663
    Prev
    Next
    INDEX
    Explanations

    also, addition

    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
    åĢı
    -0.10
    ãģ¾ãģļ
    -0.09
    .Invoke
    -0.09
    å²ij
    -0.09
    ongs
    -0.09
    åĬ¨äºº
    -0.09
    æĦŁäºº
    -0.09
    Fran
    -0.09
    å®ı大
    -0.08
    æĺ¾çĦ¶
    -0.08
    POSITIVE LOGITS
    edImage
    0.09
     importantly
    0.09
     heed
    0.08
    ayah
    0.08
    /OR
    0.08
    /API
    0.08
    è±Ĩ
    0.08
     possibilité
    0.08
    akedown
    0.08
    ä¹Łåı¯ä»¥
    0.08
    Activations Density 0.183%

    No Known Activations