© 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. 14967
    Prev
    Next
    INDEX
    Explanations

    Rebecca names

    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
     repeat
    -0.12
     reusable
    -0.11
     repeated
    -0.11
     reimb
    -0.11
     repeats
    -0.11
     receptor
    -0.10
    _re
    -0.10
     reprint
    -0.10
     replay
    -0.10
    repeat
    -0.10
    POSITIVE LOGITS
    naissance
    0.18
    deer
    0.13
    arnation
    0.12
    issance
    0.12
    ducible
    0.11
    .IGNORE
    0.11
    enderit
    0.11
    tal
    0.11
    /rec
    0.11
    itorio
    0.11
    Activations Density 0.769%

    No Known Activations