© 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. 31635
    Prev
    Next
    INDEX
    Explanations

    part of names

    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
    ergus
    -0.11
    åijĺ
    -0.10
    ize
    -0.09
    满æĦı
    -0.09
    mith
    -0.09
    æµģæ·Į
    -0.09
    yat
    -0.09
    ä¸Ģ声
    -0.08
    lick
    -0.08
    èĭĶ
    -0.08
    POSITIVE LOGITS
    æĤ£æľī
    0.09
    лев
    0.09
    åıijå±ķ缮æłĩ
    0.08
    æĭĶ
    0.08
    èľ©
    0.08
     Livingston
    0.08
     Damien
    0.08
    æĬĦ
    0.08
    caled
    0.08
    æ¾Ħæ¸ħ
    0.08
    Activations Density 0.025%

    No Known Activations