© 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. 54081
    Prev
    Next
    INDEX
    Explanations

    Portugal and Portuguese

    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
    ãģĹãģ¾
    -0.11
    etwork
    -0.11
    enen
    -0.10
    atology
    -0.10
    -quarters
    -0.10
    ãģĹãģ¾ãģĦ
    -0.10
    ãģıãĤĭ
    -0.10
    rd
    -0.10
    hardt
    -0.09
    rf
    -0.09
    POSITIVE LOGITS
    folios
    0.12
    smouth
    0.12
    åĵĩ
    0.12
    icular
    0.11
    anh
    0.10
    wor
    0.10
    IONS
    0.10
    raits
    0.10
    cle
    0.10
    quoi
    0.10
    Activations Density 0.064%

    No Known Activations