© 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. 34001
    Prev
    Next
    INDEX
    Explanations

    scholarly journals and publications

    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
     Mavericks
    -0.08
    decltype
    -0.08
    cir
    -0.08
     Valk
    -0.08
    pha
    -0.08
    fore
    -0.07
     Maver
    -0.07
    Narrated
    -0.07
     vars
    -0.07
    å¤Ħ
    -0.07
    POSITIVE LOGITS
    (vol
    0.16
     journal
    0.15
     vol
    0.14
     journals
    0.14
     Vol
    0.13
     volume
    0.13
    volume
    0.13
     VOL
    0.13
    _volume
    0.12
     Volume
    0.12
    Activations Density 0.337%

    No Known Activations