© 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. 6260
    Prev
    Next
    INDEX
    Explanations

    He/She asks or says

    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
     thems
    -0.10
     bast
    -0.10
     resemblance
    -0.09
    uto
    -0.09
     astr
    -0.09
     resembl
    -0.09
     spect
    -0.09
     bä
    -0.09
     ged
    -0.09
     Bast
    -0.09
    POSITIVE LOGITS
     likely
    0.12
     wants
    0.11
     probably
    0.11
     responsiveness
    0.11
     responded
    0.10
     wanted
    0.10
     responds
    0.10
     wanting
    0.10
    aping
    0.10
     texting
    0.10
    Activations Density 0.002%

    No Known Activations