© 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. 60682
    Prev
    Next
    INDEX
    Explanations

    inmate escape

    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
    -0.12
    éŨå¤ĸ
    -0.12
    èĥľä»»
    -0.11
    thon
    -0.10
    åĬij
    -0.10
    åīĤéĩı
    -0.10
    踩
    -0.10
    ocket
    -0.09
    fully
    -0.09
    raf
    -0.09
    POSITIVE LOGITS
    ties
    0.09
    aneous
    0.09
     Wilderness
    0.08
    renc
    0.08
    代表大ä¼ļ
    0.08
    èŁł
    0.08
    ancy
    0.08
    ãģĵãģ¨
    0.08
    .ibm
    0.08
    rez
    0.08
    Activations Density 0.012%

    No Known Activations