© 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. 16957
    Prev
    Next
    INDEX
    Explanations

    although it is

    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
     Miy
    -0.12
    ï¼ĮåĪĻ
    -0.11
     SEP
    -0.11
     cuid
    -0.11
    udi
    -0.11
     quoi
    -0.11
    SPA
    -0.10
     propia
    -0.10
    IRC
    -0.10
    bz
    -0.10
    POSITIVE LOGITS
     technically
    0.13
     nomin
    0.12
     hadn
    0.11
    exact
    0.10
     officially
    0.10
     lacks
    0.10
     wasn
    0.10
     weren
    0.10
     initially
    0.10
     hasn
    0.10
    Activations Density 0.165%

    No Known Activations