© 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. 29539
    Prev
    Next
    INDEX
    Explanations

    acknowledging something

    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
    igo
    -0.11
    åĭī强
    -0.10
    åĬŀåħ¬åİħ
    -0.09
    ãĤ¡
    -0.09
    idious
    -0.09
     Nixon
    -0.09
    iders
    -0.09
    åij¤
    -0.09
    ially
    -0.08
    quoi
    -0.08
    POSITIVE LOGITS
    NOWLED
    0.15
    ably
    0.13
    nowledge
    0.13
    nowled
    0.12
    aise
    0.10
    ìĤ¬íķŃ
    0.10
    çķĶ
    0.10
    ledged
    0.09
     receipt
    0.09
    arya
    0.09
    Activations Density 0.006%

    No Known Activations