© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5972
    Prev
    Next
    INDEX
    Explanations

    command arguments and options

    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
     WithEvents
    -0.09
    _timing
    -0.09
    .Tags
    -0.09
     COPYING
    -0.09
    iph
    -0.09
    çĿ¦
    -0.09
     Erick
    -0.08
    sched
    -0.08
    ï¸
    -0.08
    ****************************************************************************
    -0.08
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.08
    /or
    0.08
     bunch
    0.08
    å°½
    0.07
    flu
    0.07
    èĩªå¦Ĥ
    0.07
    åĴĮæĬĢæľ¯
    0.07
    èIJ¥
    0.07
     followed
    0.07
    Forum
    0.07
    Activations Density 0.714%

    No Known Activations