© 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. 48965
    Prev
    Next
    INDEX
    Explanations

    type, kind, or category

    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
    åİŁå§ĭ
    -0.09
    ark
    -0.09
    tru
    -0.08
    é©·
    -0.08
    ä½ľåĵģåĨħ容
    -0.08
    CString
    -0.08
    æµģæ°´
    -0.08
     fort
    -0.08
     pis
    -0.08
     вÑģÑıк
    -0.08
    POSITIVE LOGITS
    ç±»åŀĭçļĦ
    0.22
    ç±»åŀĭ
    0.19
     type
    0.19
     types
    0.18
     tipo
    0.16
     kind
    0.16
     kinds
    0.14
    type
    0.14
     jenis
    0.14
    _type
    0.13
    Activations Density 0.168%

    No Known Activations