© 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. 47758
    Prev
    Next
    INDEX
    Explanations

    AM/PM timestamps

    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
    <|fim_suffix|>
    -0.09
     Bast
    -0.07
    ,");↵
    -0.07
     ment
    -0.07
    /widget
    -0.07
    ows
    -0.07
    éo
    -0.07
     prick
    -0.07
     innoc
    -0.06
     gre
    -0.06
    POSITIVE LOGITS
    ouce
    0.11
     fours
    0.10
     retVal
    0.10
    iza
    0.10
    OrCreate
    0.10
    /cal
    0.09
    ELY
    0.09
     chaud
    0.09
    itime
    0.09
     Haw
    0.09
    Activations Density 0.040%

    No Known Activations