© 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. 15083
    Prev
    Next
    INDEX
    Explanations

    prefixes followed by specific word beginnings

    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
     Som
    -0.12
    ENTS
    -0.11
    verts
    -0.10
     Mond
    -0.10
    igits
    -0.10
     Techn
    -0.10
    ements
    -0.10
    -olds
    -0.10
    _some
    -0.10
    ients
    -0.10
    POSITIVE LOGITS
    /non
    0.09
     Jens
    0.07
    erable
    0.07
    -/
    0.07
     Lager
    0.07
    )\<
    0.07
     Bust
    0.07
    (EFFECT
    0.07
    teness
    0.07
     Rudd
    0.07
    Activations Density 0.822%

    No Known Activations