© 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. 24230
    Prev
    Next
    INDEX
    Explanations

    company 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
    Negative Logits
    è§ģæķĪ
    -0.09
    å§Ŀ
    -0.09
    entr
    -0.09
    åĨĴéĻ©
    -0.08
    åħĶ
    -0.08
    handles
    -0.08
    mmc
    -0.08
    rng
    -0.08
    ines
    -0.08
    Ùħص
    -0.08
    POSITIVE LOGITS
    scribe
    0.10
    å¤ļ项
    0.09
    ç³Ł
    0.09
     UIL
    0.09
    è¿ľæĸ¹
    0.09
    ä¸Ģå¹ķ
    0.09
    秣
    0.08
    éªĬ
    0.08
    ä¸Ģ份
    0.08
    åĭº
    0.08
    Activations Density 0.042%

    No Known Activations