© 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. 34961
    Prev
    Next
    INDEX
    Explanations

    recipe instructions

    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
    ingly
    -0.10
    ance
    -0.10
    OAD
    -0.10
    ugi
    -0.09
    ances
    -0.08
    iju
    -0.08
     mục
    -0.08
    FI
    -0.08
    ument
    -0.08
    ajan
    -0.08
    POSITIVE LOGITS
    大åħ¨
    0.11
    èī¯å¿ĥ
    0.09
    éĩįæķ´
    0.09
    åİŁæĸĩ
    0.09
    游åĩ»éĺŁ
    0.09
    ãģĦãģ¾
    0.09
    ä¸ŃåIJ«æľī
    0.08
    æĺ´
    0.08
    èijº
    0.08
    é¹°
    0.08
    Activations Density 0.040%

    No Known Activations