© 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. 33833
    Prev
    Next
    INDEX
    Explanations

    user friendly interfaces

    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
    Not in Any Lists

    No Comments

    Negative Logits
    urator
    -0.10
     blat
    -0.09
     conclus
    -0.09
    chner
    -0.09
     bunk
    -0.08
     precursor
    -0.08
     prec
    -0.08
    ny
    -0.08
    iator
    -0.08
     Prec
    -0.08
    POSITIVE LOGITS
    -friendly
    0.30
     friendly
    0.29
    friendly
    0.26
     Friendly
    0.23
    Friendly
    0.21
    riendly
    0.18
     interface
    0.17
    åıĭ
    0.17
     FRIEND
    0.17
    -centric
    0.16
    Activations Density 0.066%

    No Known Activations