© 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. 10919
    Prev
    Next
    INDEX
    Explanations

    Palestinian state

    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»ĺãģij
    -0.09
    elen
    -0.09
    æ·Į
    -0.09
    tip
    -0.09
    otch
    -0.08
     AMAZ
    -0.08
    |array
    -0.08
    OTS
    -0.08
    lessly
    -0.08
    èİŀ
    -0.08
    POSITIVE LOGITS
    icious
    0.10
     Ñģебе
    0.09
    æŦ
    0.09
    çĸ£
    0.09
    -owned
    0.09
    /ne
    0.09
    /black
    0.08
    漪
    0.08
    峪
    0.08
    wich
    0.08
    Activations Density 0.008%

    No Known Activations