© 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. 112697
    Prev
    Next
    INDEX
    Explanations

    logging

    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
    erez
    -0.10
    -corner
    -0.10
    LogLevel
    -0.10
    yat
    -0.10
    errer
    -0.10
    eker
    -0.10
    wald
    -0.10
    á»ı
    -0.10
    ancel
    -0.10
    construct
    -0.09
    POSITIVE LOGITS
    arith
    0.23
    gers
    0.21
    gings
    0.20
    gable
    0.18
    radouro
    0.15
    GING
    0.14
    gin
    0.13
    ically
    0.13
    ging
    0.13
    raphic
    0.12
    Activations Density 0.070%

    No Known Activations