© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38425
    Prev
    Next
    INDEX
    Explanations

    lessons and topics

    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
    å©¿
    -0.10
    ï¸ı
    -0.09
    ÑģÑĮ
    -0.09
    ulence
    -0.09
    -0.09
    ols
    -0.09
    sdale
    -0.09
    /Linux
    -0.09
    utive
    -0.08
    辫
    -0.08
    POSITIVE LOGITS
    naire
    0.14
    naires
    0.12
    arium
    0.09
     fate
    0.09
    mania
    0.09
    olle
    0.09
    ambre
    0.09
     Fate
    0.09
    undry
    0.08
    åŀĭä¼ģä¸ļ
    0.08
    Activations Density 0.011%

    No Known Activations