© 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. 15278
    Prev
    Next
    INDEX
    Explanations

    comparable to or similar to

    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
    itos
    -0.11
    egg
    -0.11
    reon
    -0.11
    bla
    -0.10
    ooter
    -0.10
    eya
    -0.09
     Chambers
    -0.09
    framework
    -0.09
    iben
    -0.09
    len
    -0.09
    POSITIVE LOGITS
     maybe
    0.18
     arguably
    0.17
     MORE
    0.17
     Worse
    0.16
     surpassed
    0.16
     perhaps
    0.15
     possibly
    0.15
     worse
    0.15
    maybe
    0.15
    -plus
    0.15
    Activations Density 0.228%

    No Known Activations