© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13874
    Prev
    Next
    INDEX
    Explanations

    instructions not to modify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    wid
    -0.11
    alle
    -0.10
     births
    -0.10
     sof
    -0.10
    stra
    -0.10
    Bind
    -0.10
     rendez
    -0.10
    athan
    -0.10
     promises
    -0.10
    cura
    -0.09
    POSITIVE LOGITS
     anything
    0.11
    boo
    0.09
     Fuk
    0.09
     untouched
    0.09
    /use
    0.09
     Pra
    0.09
     redesign
    0.09
     valu
    0.08
     unt
    0.08
    anything
    0.08
    Activations Density 0.040%

    No Known Activations