© 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. 14890
    Prev
    Next
    INDEX
    Explanations

    owner's name followed by a noun

    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
    TR
    -0.08
     Bernardino
    -0.07
    omatic
    -0.06
    [:]
    -0.06
    arium
    -0.06
     amidst
    -0.06
     var
    -0.06
     substantive
    -0.06
     submar
    -0.06
     postData
    -0.06
    POSITIVE LOGITS
     pov
    0.13
     reco
    0.13
     journey
    0.13
     POV
    0.12
    /th
    0.12
    jour
    0.11
     hitch
    0.11
    rie
    0.11
    Ìģ
    0.11
     next
    0.11
    Activations Density 0.013%

    No Known Activations