© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90482
    Prev
    Next
    INDEX
    Explanations

    height measurements

    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
    [op
    -0.11
     Zum
    -0.11
     "\↵
    -0.10
    nad
    -0.10
     age
    -0.10
    ãĥŃãĤ°
    -0.10
     Ner
    -0.10
     ost
    -0.10
    /address
    -0.10
    963
    -0.10
    POSITIVE LOGITS
     tall
    0.12
    ½
    0.08
    0
    0.08
     Tall
    0.08
    ish
    0.08
    ¦
    0.08
    6
    0.07
    ª
    0.07
     medium
    0.07
    ezier
    0.07
    Activations Density 0.010%

    No Known Activations