© 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. 14719
    Prev
    Next
    INDEX
    Explanations

    Smith &

    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
    isse
    -0.11
    NING
    -0.10
    ift
    -0.10
    ض
    -0.10
    itu
    -0.10
    /sm
    -0.09
    ookie
    -0.09
    itate
    -0.09
    istics
    -0.09
    ISC
    -0.09
    POSITIVE LOGITS
    sonian
    0.24
    ers
    0.18
    wick
    0.17
    son
    0.15
    ies
    0.14
    urst
    0.13
    ere
    0.12
    ells
    0.11
    yard
    0.11
    SON
    0.11
    Activations Density 0.027%

    No Known Activations