© 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. 8023
    Prev
    Next
    INDEX
    Explanations

    letters followed by numbers or words

    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
     compuls
    -0.09
    pun
    -0.09
     pun
    -0.08
     vener
    -0.08
    ABCDEFG
    -0.08
    .ws
    -0.07
     ÑģÑģÑĭл
    -0.07
     reigning
    -0.07
     Wich
    -0.07
    itr
    -0.07
    POSITIVE LOGITS
     exempl
    0.11
    ACES
    0.11
    é¦ĸ
    0.10
     Whisper
    0.10
     Variant
    0.10
     Ends
    0.10
    -pic
    0.10
     Closure
    0.10
     jou
    0.10
     Deleted
    0.09
    Activations Density 0.031%

    No Known Activations