© 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. 47665
    Prev
    Next
    INDEX
    Explanations

    (C) copyright notices

    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
    amera
    -0.11
    ache
    -0.11
    oding
    -0.11
    ancel
    -0.11
    olumn
    -0.11
    lose
    -0.11
    arded
    -0.10
    oeff
    -0.10
    arta
    -0.10
    _ci
    -0.10
    POSITIVE LOGITS
    ifornia
    0.13
    mere
    0.12
    indrical
    0.11
    .fetchone
    0.10
    nip
    0.10
    apult
    0.10
    égorie
    0.10
    itious
    0.10
    bearer
    0.10
    -cut
    0.10
    Activations Density 2.907%

    No Known Activations