© 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. 91108
    Prev
    Next
    INDEX
    Explanations

    abbreviations for titles before names

    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
    room
    -0.10
     irresist
    -0.10
     photographer
    -0.10
     empres
    -0.10
     Leban
    -0.09
    оваÑĢ
    -0.09
     Kron
    -0.09
    InvalidOperationException
    -0.09
     Draco
    -0.09
     Carr
    -0.09
    POSITIVE LOGITS
    ugs
    0.12
     explains
    0.10
    agan
    0.10
     ted
    0.10
     habil
    0.10
     Tage
    0.09
     Mona
    0.09
     uninterrupted
    0.08
     Thema
    0.08
     Mark
    0.08
    Activations Density 0.080%

    No Known Activations