© 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. 5147
    Prev
    Next
    INDEX
    Explanations

    erbiger

    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
    er
    -0.13
    l
    -0.13
    tn
    -0.12
    erre
    -0.12
    eria
    -0.12
    rary
    -0.12
    aru
    -0.12
    eur
    -0.11
    eron
    -0.11
    ron
    -0.11
    POSITIVE LOGITS
    alled
    0.12
    ent
    0.10
    ourse
    0.09
    ap
    0.09
    lesh
    0.09
    osa
    0.09
    idge
    0.08
    em
    0.08
    pd
    0.08
    ombs
    0.08
    Activations Density 0.181%

    No Known Activations