© 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. 6411
    Prev
    Next
    INDEX
    Explanations

    darkened, dark room, darkness

    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
     Isl
    -0.11
    -hash
    -0.10
    /ag
    -0.09
    ,application
    -0.09
     Werner
    -0.09
    -selector
    -0.09
    /app
    -0.09
     unearth
    -0.09
     stirring
    -0.09
     Influ
    -0.09
    POSITIVE LOGITS
    ened
    0.18
    ening
    0.14
     except
    0.12
    enment
    0.11
     humour
    0.11
    room
    0.10
    ennes
    0.10
    Std
    0.10
     humor
    0.10
     Ages
    0.10
    Activations Density 0.031%

    No Known Activations