© 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. 31950
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
     pit
    -0.12
     unwitting
    -0.12
    imson
    -0.11
    /if
    -0.11
    lest
    -0.11
    /generated
    -0.11
     appe
    -0.11
    ynos
    -0.11
    åĬŁ
    -0.11
    engan
    -0.11
    POSITIVE LOGITS
     seeking
    0.15
     looking
    0.15
     located
    0.13
     available
    0.13
    seek
    0.13
     open
    0.12
    looking
    0.12
     currently
    0.11
     flexible
    0.11
    available
    0.11
    Activations Density 0.021%

    No Known Activations