© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30014
    Prev
    Next
    INDEX
    Explanations

    top ranked performers

    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
     extremes
    -0.11
     damned
    -0.10
     Salv
    -0.10
     lurking
    -0.10
    omore
    -0.10
    iez
    -0.10
    packed
    -0.09
    /link
    -0.09
     harmed
    -0.09
    alley
    -0.09
    POSITIVE LOGITS
     earners
    0.14
    -rated
    0.13
     rated
    0.13
     ranked
    0.13
    -ranked
    0.12
     contender
    0.12
    /top
    0.11
     rankings
    0.11
     scorer
    0.11
     performers
    0.10
    Activations Density 0.194%

    No Known Activations