© 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. 33265
    Prev
    Next
    INDEX
    Explanations

    serving, portions, dose, helping

    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
    ä¸ĢèĦļ
    -0.10
    çĽı
    -0.09
    åŀĽ
    -0.09
     diss
    -0.09
    象
    -0.08
    .Detail
    -0.08
    imat
    -0.08
    rive
    -0.08
     Bounty
    -0.08
    ãģķãĤī
    -0.08
    POSITIVE LOGITS
    è°¯
    0.10
     Leon
    0.09
    wise
    0.08
    åİļåİļ
    0.08
    mes
    0.08
     Ñģог
    0.08
    人身
    0.08
    à¸ĵ
    0.08
     Kemp
    0.08
    esk
    0.08
    Activations Density 0.003%

    No Known Activations