© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48544
    Prev
    Next
    INDEX
    Explanations

    work of fiction

    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
     tutors
    -0.12
    odie
    -0.12
     succ
    -0.11
     suites
    -0.11
     anchors
    -0.11
    OV
    -0.11
    -ms
    -0.11
     Michelle
    -0.11
    succ
    -0.11
    itched
    -0.11
    POSITIVE LOGITS
     fiction
    0.09
     Nas
    0.08
    nas
    0.08
     Wass
    0.07
    umn
    0.07
    chet
    0.07
    -half
    0.07
     Wes
    0.07
     Tot
    0.07
     halves
    0.07
    Activations Density 0.002%

    No Known Activations