© 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. 50108
    Prev
    Next
    INDEX
    Explanations

    seen

    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
    eren
    -0.10
    cob
    -0.10
    plr
    -0.10
    iled
    -0.10
     Miranda
    -0.09
    bench
    -0.09
     milan
    -0.08
     hur
    -0.08
     Reyn
    -0.08
    tones
    -0.08
    POSITIVE LOGITS
    /read
    0.14
    efore
    0.11
    fad
    0.11
     documentaries
    0.10
    iste
    0.10
     seen
    0.10
    ews
    0.10
    otec
    0.10
    Elf
    0.10
    fos
    0.10
    Activations Density 0.019%

    No Known Activations