© 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. 59061
    Prev
    Next
    INDEX
    Explanations

    cause negative outcomes

    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
    èĻ±
    -0.11
    쯤
    -0.11
    rose
    -0.10
    oret
    -0.10
    å®ļäºĨ
    -0.10
    sson
    -0.09
    ights
    -0.09
    ä¹ĭä½ľ
    -0.09
    åŀļ
    -0.09
    ilen
    -0.09
    POSITIVE LOGITS
     havoc
    0.13
     cél
    0.11
    fully
    0.10
    lessly
    0.08
    forth
    0.08
    ivities
    0.08
    åŃ½
    0.08
    íĴĪ
    0.08
    åıĪ好
    0.08
    ught
    0.08
    Activations Density 0.071%

    No Known Activations