© 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. 47546
    Prev
    Next
    INDEX
    Explanations

    sen 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
    oreach
    -0.10
    è¿Ń
    -0.09
    losure
    -0.09
    èĩªå¦Ĥ
    -0.09
    odef
    -0.09
    çªģçł´
    -0.09
     hop
    -0.08
    ocre
    -0.08
     маÑĢÑĪ
    -0.08
    yps
    -0.08
    POSITIVE LOGITS
    sen
    0.12
    eness
    0.11
    ness
    0.11
    sson
    0.11
    set
    0.09
     Ãĺ
    0.09
    NESS
    0.08
    sem
    0.08
    son
    0.08
     unpopular
    0.08
    Activations Density 0.079%

    No Known Activations