© 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. 49251
    Prev
    Next
    INDEX
    Explanations

    body parts, places, and abstract nouns followed by verbs

    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
     unfavor
    -0.11
     encount
    -0.10
    ucker
    -0.10
     unsuccessfully
    -0.10
     doch
    -0.10
     differently
    -0.10
    /=
    -0.09
     trag
    -0.09
     offs
    -0.09
     associ
    -0.09
    POSITIVE LOGITS
     meanwhile
    0.19
     however
    0.14
     soon
    0.12
     then
    0.12
     meantime
    0.11
     continued
    0.10
    however
    0.10
     slowly
    0.10
     seemed
    0.10
     itself
    0.10
    Activations Density 0.017%

    No Known Activations