© 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. 30834
    Prev
    Next
    INDEX
    Explanations

    sharp edges or points

    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
    003
    -0.11
     Roll
    -0.11
     Kov
    -0.11
     Boo
    -0.10
    jak
    -0.10
     Kem
    -0.10
     calf
    -0.10
     Milk
    -0.10
    077
    -0.10
     roll
    -0.10
    POSITIVE LOGITS
     sharp
    0.25
     jag
    0.20
    Sharp
    0.20
     Sharp
    0.19
    sharp
    0.19
     rocks
    0.18
     spikes
    0.18
     sharper
    0.18
     sharpen
    0.17
     nails
    0.16
    Activations Density 0.210%

    No Known Activations