© 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. 89726
    Prev
    Next
    INDEX
    Explanations

    preceded by, non-precedential, precedential

    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
    acob
    -0.10
    ìĭĿ
    -0.10
    izados
    -0.10
    izando
    -0.10
    washing
    -0.10
    immel
    -0.09
    Disposed
    -0.09
    yard
    -0.09
    station
    -0.09
    izzazione
    -0.09
    POSITIVE LOGITS
    ingly
    0.14
    ents
    0.12
    ence
    0.10
    ely
    0.10
    ences
    0.10
    ptions
    0.10
    eed
    0.09
    iences
    0.09
    ently
    0.09
    iber
    0.09
    Activations Density 0.213%

    No Known Activations