© 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. 7117
    Prev
    Next
    INDEX
    Explanations

    flexibility, mobility, motion, strength

    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
     conv
    -0.10
     firmly
    -0.09
    rescia
    -0.09
    chor
    -0.09
     Crack
    -0.09
    linger
    -0.09
     qu
    -0.09
     WEB
    -0.09
     appropriately
    -0.09
    urity
    -0.09
    POSITIVE LOGITS
     joints
    0.12
     joint
    0.11
    joint
    0.10
    Joint
    0.10
     Stella
    0.10
    PIO
    0.09
     advertised
    0.09
     Dud
    0.09
    /card
    0.09
     FITNESS
    0.09
    Activations Density 0.025%

    No Known Activations