© 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. 5243
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
     blind
    -0.08
     shred
    -0.07
     hil
    -0.07
     tens
    -0.07
    .grade
    -0.07
     torn
    -0.07
     halfway
    -0.07
     ent
    -0.07
     attraction
    -0.07
     Swagger
    -0.07
    POSITIVE LOGITS
     frequency
    0.54
     Frequency
    0.46
    frequency
    0.44
     frequencies
    0.43
    Frequency
    0.41
    é¢ij
    0.41
     frequent
    0.40
     freq
    0.40
    -frequency
    0.39
     Frequ
    0.36
    Activations Density 0.610%

    No Known Activations