© 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. 114274
    Prev
    Next
    INDEX
    Explanations

    name, nickname, or alias

    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
    rift
    -0.08
     unnamed
    -0.07
    urg
    -0.07
     ca
    -0.07
     consequence
    -0.07
    /io
    -0.07
    nar
    -0.07
     frost
    -0.07
     Kai
    -0.07
     Name
    -0.07
    POSITIVE LOGITS
    pron
    0.18
     surname
    0.17
     nickname
    0.17
     nicknamed
    0.16
     pronounced
    0.16
     pronounce
    0.15
     spelled
    0.15
     subtitle
    0.14
     shortened
    0.14
     alias
    0.14
    Activations Density 0.083%

    No Known Activations