© 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. 32239
    Prev
    Next
    INDEX
    Explanations

    defrauded, rob, from people

    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
    æĵį
    -0.10
    .dispatch
    -0.09
    .statusText
    -0.09
    ä¸Ģåī¯
    -0.09
    .tim
    -0.09
    chor
    -0.09
    нÑĮ
    -0.09
    enis
    -0.08
     lecturer
    -0.08
    çħ§æĸĻ
    -0.08
    POSITIVE LOGITS
    lias
    0.09
    éļħ
    0.09
    à¹Ģรา
    0.09
    ulas
    0.08
    æĮ¹
    0.08
     us
    0.08
    devil
    0.08
     Ñģобой
    0.08
     innocent
    0.08
     odom
    0.08
    Activations Density 0.014%

    No Known Activations