© 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. 47655
    Prev
    Next
    INDEX
    Explanations

    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
    avs
    -0.10
    728
    -0.09
     loosen
    -0.09
    osas
    -0.09
     loos
    -0.09
    Uri
    -0.09
    leh
    -0.09
    AWN
    -0.09
     eagle
    -0.09
     compens
    -0.08
    POSITIVE LOGITS
     aloud
    0.37
     readings
    0.25
     reading
    0.24
     read
    0.24
     orally
    0.22
     narration
    0.21
     pronunciation
    0.21
     reads
    0.21
     narr
    0.21
     Reading
    0.20
    Activations Density 0.134%

    No Known Activations