© 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. 63866
    Prev
    Next
    INDEX
    Explanations

    endpoint devices, remote control, instruments

    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
    åºij
    -0.10
    è°ħ
    -0.10
    _flight
    -0.10
    èĩªè´Ł
    -0.09
    rag
    -0.09
    çĥ«
    -0.09
    frag
    -0.09
    éĿĻçĶµ
    -0.09
    antis
    -0.09
     playable
    -0.09
    POSITIVE LOGITS
     Gle
    0.09
    仪表
    0.09
    çİ°åľº
    0.09
     instruments
    0.08
    amera
    0.08
    仪åĻ¨
    0.08
    亲è¿ij
    0.08
    Ñīи
    0.08
     instrument
    0.08
     bi
    0.08
    Activations Density 0.064%

    No Known Activations