© 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. 89764
    Prev
    Next
    INDEX
    Explanations

    groove, latch, slot, notch, ratchet

    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
    *time
    -0.13
    ofday
    -0.13
     involuntary
    -0.12
    /person
    -0.12
    resse
    -0.12
    å§
    -0.11
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.11
     TOUCH
    -0.11
     Map
    -0.11
    .sul
    -0.11
    POSITIVE LOGITS
     groove
    0.13
     locking
    0.12
     gro
    0.12
     recess
    0.12
     notch
    0.11
     slots
    0.11
     mating
    0.10
     securing
    0.10
     cham
    0.10
    locking
    0.09
    Activations Density 0.835%

    No Known Activations