© 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. 7771
    Prev
    Next
    INDEX
    Explanations

    research institutes and studies

    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
     B
    -0.07
    enn
    -0.06
    iar
    -0.06
    onal
    -0.06
    <|fim_suffix|>
    -0.06
     inter
    -0.06
     en
    -0.06
    Åĵ
    -0.06
    aro
    -0.05
     L
    -0.05
    POSITIVE LOGITS
    serter
    0.13
     Hairst
    0.13
    <quote
    0.12
     hairstyle
    0.12
    .infinity
    0.12
     männ
    0.11
    imenti
    0.11
     Vanity
    0.11
    [Test
    0.11
    {/*
    0.11
    Activations Density 0.121%

    No Known Activations