© 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. 89142
    Prev
    Next
    INDEX
    Explanations

    cleft, cleave, cloves

    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
    Qui
    -0.11
    ات
    -0.10
    olest
    -0.09
    pla
    -0.09
     malignant
    -0.09
    abble
    -0.09
    bag
    -0.09
     brightest
    -0.09
    istring
    -0.09
    abbo
    -0.09
    POSITIVE LOGITS
    ed
    0.17
    edBy
    0.13
    edly
    0.12
     undef
    0.11
    edException
    0.10
     cle
    0.09
     apart
    0.09
    -divider
    0.09
     crest
    0.09
    eson
    0.09
    Activations Density 0.001%

    No Known Activations