© 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. 26479
    Prev
    Next
    INDEX
    Explanations

    speaking or reading aloud

    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
    serv
    -0.09
     rond
    -0.09
    ion
    -0.09
    ions
    -0.08
    rex
    -0.08
     gist
    -0.08
     ourselves
    -0.08
     serv
    -0.08
    StringBuilder
    -0.08
    achi
    -0.08
    POSITIVE LOGITS
    /write
    0.15
     aloud
    0.13
     volumes
    0.13
     candid
    0.11
     tome
    0.11
    /type
    0.11
     louder
    0.10
     softly
    0.10
    /read
    0.10
     frankly
    0.10
    Activations Density 0.045%

    No Known Activations