© 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. 982
    Prev
    Next
    INDEX
    Explanations

    van der

    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
     Haram
    -0.09
    ëŀĢ
    -0.09
    æ·±åħ¥äººå¿ĥ
    -0.09
    ined
    -0.08
    æ°¾
    -0.08
    ingly
    -0.08
    æĢģ
    -0.08
    让æĤ¨
    -0.08
    çī¹æľĹ
    -0.08
    æªĶ
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.11
    о
    0.11
     dolayı
    0.10
    ishing
    0.10
    aroo
    0.10
    forth
    0.09
    iglia
    0.09
    brick
    0.09
    riott
    0.09
    ILLA
    0.09
    Activations Density 0.045%

    No Known Activations