© 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. 112479
    Prev
    Next
    INDEX
    Explanations

    is living

    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
     climax
    -0.09
    apon
    -0.09
     Hansen
    -0.08
    isser
    -0.07
     carn
    -0.07
     Anc
    -0.07
    _none
    -0.07
     aller
    -0.07
     other
    -0.07
    ologically
    -0.07
    POSITIVE LOGITS
    yal
    0.12
    _story
    0.10
    Floating
    0.10
     bloody
    0.10
    ajo
    0.10
    NoSuch
    0.10
     STORY
    0.10
     guts
    0.10
    rias
    0.10
    MethodName
    0.10
    Activations Density 0.002%

    No Known Activations