© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90563
    Prev
    Next
    INDEX
    Explanations

    as seen in / publications / pdf files

    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
    gger
    -0.11
    eka
    -0.11
    vince
    -0.11
    wend
    -0.10
    inke
    -0.10
    Ñħод
    -0.10
     Asked
    -0.10
    rim
    -0.10
     Colleg
    -0.10
    wyn
    -0.10
    POSITIVE LOGITS
     progresses
    0.11
     result
    0.09
    cribed
    0.09
     instructed
    0.08
    cert
    0.08
     siden
    0.08
     progressed
    0.08
    -is
    0.08
    uded
    0.08
     basis
    0.07
    Activations Density 1.445%

    No Known Activations