© 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. 11660
    Prev
    Next
    INDEX
    Explanations

    fan of

    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
     prest
    -0.09
     createAction
    -0.08
    æ¡ĪåŃIJ
    -0.08
    å¤Ļ
    -0.08
    ufs
    -0.08
    æįIJ款
    -0.08
    Flo
    -0.08
     Tig
    -0.08
    éĩijåĪļ
    -0.08
    óng
    -0.08
    POSITIVE LOGITS
    ampo
    0.10
    èĩ§
    0.10
    ANC
    0.10
    byn
    0.09
    é¼ĵ
    0.09
     Kear
    0.09
    é¹Ń
    0.09
    VIC
    0.09
    ITED
    0.08
     olduk
    0.08
    Activations Density 0.006%

    No Known Activations