© 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. 25604
    Prev
    Next
    INDEX
    Explanations

    possibly followed by speculation

    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
     basically
    -0.17
    peg
    -0.14
     certainly
    -0.13
     practically
    -0.13
     obviously
    -0.12
     surely
    -0.12
     undoubtedly
    -0.12
    ening
    -0.12
     definitely
    -0.12
    ened
    -0.11
    POSITIVE LOGITS
    /pro
    0.20
     could
    0.12
    could
    0.11
     Could
    0.10
     podrÃŃa
    0.10
     (?
    0.10
     might
    0.10
    idon
    0.09
     sogar
    0.09
    Could
    0.09
    Activations Density 0.027%

    No Known Activations