© 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. 113984
    Prev
    Next
    INDEX
    Explanations

    'u' followed by a consonant/vowel

    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
    /use
    -0.10
     unusual
    -0.10
     unfortunate
    -0.10
    IGO
    -0.09
    opoulos
    -0.09
    /users
    -0.09
    /un
    -0.08
    ìŀ¬
    -0.08
    utils
    -0.08
    alled
    -0.08
    POSITIVE LOGITS
    querque
    0.15
    elage
    0.15
    rious
    0.14
    ulent
    0.13
    venile
    0.13
    icrous
    0.12
    eltas
    0.12
    ********************
    0.12
    ifix
    0.12
    rients
    0.12
    Activations Density 2.242%

    No Known Activations