© 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. 61094
    Prev
    Next
    INDEX
    Explanations

    Geneva and Vienna

    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
     Shir
    -0.10
     eventual
    -0.09
    ¼
    -0.08
    gend
    -0.08
     Celebrity
    -0.08
    大çīĩ
    -0.08
    lymp
    -0.08
     Dod
    -0.08
    erre
    -0.08
    efault
    -0.08
    POSITIVE LOGITS
    ç¨İåĬ¡å±Ģ
    0.10
    bole
    0.10
    IZER
    0.09
    ÑģÑĤÑĥп
    0.09
    stem
    0.09
    ised
    0.08
    ensis
    0.08
    çľĻ
    0.08
    _ARGUMENT
    0.08
    åĩĨåħ¥
    0.08
    Activations Density 0.005%

    No Known Activations