© 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. 16752
    Prev
    Next
    INDEX
    Explanations

    into the

    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
     into
    -0.14
    Into
    -0.12
     Into
    -0.11
    lessness
    -0.11
    mar
    -0.10
    lessly
    -0.10
    .into
    -0.10
     INTO
    -0.10
     onto
    -0.10
     beyond
    -0.10
    POSITIVE LOGITS
    /from
    0.21
    /out
    0.19
     thirds
    0.13
     fruition
    0.13
    a
    0.12
     obliv
    0.12
    aal
    0.12
    /by
    0.12
     place
    0.12
    appropri
    0.11
    Activations Density 0.113%

    No Known Activations