© 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. 29433
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE html PUBLIC "-//W3C"

    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
     ETA
    -0.11
     sud
    -0.10
    dbuf
    -0.10
    |;↵
    -0.10
    -set
    -0.10
     reprodu
    -0.10
     inferior
    -0.10
     oppress
    -0.10
    gli
    -0.09
    094
    -0.09
    POSITIVE LOGITS
     conjug
    0.08
    lasting
    0.08
     CCTV
    0.07
    ibur
    0.07
    ãģ¾ãģŁ
    0.07
    ump
    0.07
     ease
    0.07
     litt
    0.07
    weekly
    0.07
    oice
    0.07
    Activations Density 0.002%

    No Known Activations