© 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. 6392
    Prev
    Next
    INDEX
    Explanations

    author:

    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
    ç¿Ľ
    -0.09
    缣
    -0.09
    å®Ļ
    -0.09
    æĪĺåıĭ
    -0.09
    åıijè¾¾
    -0.08
    çīºçī²
    -0.08
    嫦
    -0.08
    ä½ıæīĢ
    -0.08
    çĦľ
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    aire
    0.09
    enen
    0.09
    èħ´
    0.08
    èļĬ
    0.08
    éĺµéĺµ
    0.08
    _SO
    0.08
     âĶľ
    0.08
    .com
    0.08
    tre
    0.08
    erin
    0.08
    Activations Density 0.064%

    No Known Activations