© 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. 47214
    Prev
    Next
    INDEX
    Explanations

    -type or -sized objects

    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
     imped
    -0.11
     Machinery
    -0.11
     franch
    -0.10
     Pref
    -0.10
     elig
    -0.09
     machinery
    -0.09
     cor
    -0.09
     Robotics
    -0.09
     pref
    -0.09
     contr
    -0.08
    POSITIVE LOGITS
    -style
    0.18
    -sized
    0.16
    -type
    0.14
    /small
    0.14
     tucked
    0.14
    åŀĭ
    0.13
     style
    0.13
    -shaped
    0.12
     small
    0.12
     smaller
    0.11
    Activations Density 0.028%

    No Known Activations