© 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. 30971
    Prev
    Next
    INDEX
    Explanations

    in, all, this, as, the, it

    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
    ведиÑĤе
    -0.20
    ses
    -0.18
    обав
    -0.17
    paring
    -0.15
    ighbors
    -0.13
    ÑĪибка
    -0.13
    leccion
    -0.12
    vertiser
    -0.12
    asured
    -0.12
    ContentLoaded
    -0.12
    POSITIVE LOGITS
    etheless
    0.42
    odore
    0.40
    adays
    0.40
    greSQL
    0.30
    xiety
    0.29
    bsites
    0.29
    jamin
    0.29
    tlement
    0.27
    achusetts
    0.26
    phalt
    0.26
    Activations Density 3.399%

    No Known Activations