© 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. 25494
    Prev
    Next
    INDEX
    Explanations

    bone related terms

    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
    dom
    -0.13
     Morton
    -0.13
    rog
    -0.12
    reg
    -0.11
    ter
    -0.11
    ures
    -0.11
    ión
    -0.11
    roid
    -0.11
    time
    -0.11
    loo
    -0.11
    POSITIVE LOGITS
     marrow
    0.18
    less
    0.11
    breaker
    0.11
    /cart
    0.10
    -breaking
    0.09
    lessly
    0.08
     MAR
    0.08
    hill
    0.08
    fee
    0.08
    beam
    0.08
    Activations Density 0.015%

    No Known Activations