© 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. 19287
    Prev
    Next
    INDEX
    Explanations

    Turkey

    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
    illy
    -0.09
    urer
    -0.08
    è¡ħ
    -0.08
    ingles
    -0.08
    /tutorial
    -0.08
     jÄĻzyk
    -0.08
    illes
    -0.08
    æĬ¼ãģĹ
    -0.08
    illez
    -0.08
    OrUpdate
    -0.08
    POSITIVE LOGITS
    sey
    0.10
    ÑĤÑĢ
    0.10
    onom
    0.10
    unch
    0.09
    çĬ¶
    0.09
    ture
    0.09
    itchen
    0.08
     Zurich
    0.08
    mania
    0.08
    gence
    0.08
    Activations Density 0.006%

    No Known Activations