© 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. 49556
    Prev
    Next
    INDEX
    Explanations

    Bog and related words

    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
     Cutting
    -0.12
     Casc
    -0.10
    bare
    -0.09
    lico
    -0.09
    ন
    -0.09
     cutting
    -0.09
    ecast
    -0.09
    ould
    -0.09
     cutoff
    -0.09
     cloudy
    -0.09
    POSITIVE LOGITS
    dan
    0.14
    ey
    0.13
     down
    0.11
    eyed
    0.11
     Down
    0.11
    usz
    0.11
     bog
    0.10
    gs
    0.10
    ges
    0.10
     Bog
    0.10
    Activations Density 0.010%

    No Known Activations