© 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. 16633
    Prev
    Next
    INDEX
    Explanations

    scoring shots

    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
     rave
    -0.11
     Quar
    -0.10
     tracing
    -0.10
     Snowden
    -0.10
     Skin
    -0.10
     expose
    -0.10
    kas
    -0.10
     slicing
    -0.09
    ennen
    -0.09
    maps
    -0.09
    POSITIVE LOGITS
     shooting
    0.22
     shots
    0.22
     shot
    0.22
     shootout
    0.21
     Shots
    0.21
     shoot
    0.21
     shooters
    0.21
     shooter
    0.20
     scoring
    0.20
     Shooting
    0.19
    Activations Density 0.268%

    No Known Activations