© 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. 115104
    Prev
    Next
    INDEX
    Explanations

    throwing 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
    ories
    -0.09
     sidewalks
    -0.08
    /go
    -0.08
    iek
    -0.08
     Vie
    -0.08
     Gener
    -0.08
     Katz
    -0.07
     SIN
    -0.07
    CALE
    -0.07
     parachute
    -0.07
    POSITIVE LOGITS
     projectiles
    0.15
     threw
    0.13
     thrown
    0.13
     projectile
    0.13
     barrage
    0.13
     objects
    0.12
     pellets
    0.12
    balls
    0.12
     throwing
    0.11
     throws
    0.11
    Activations Density 0.078%

    No Known Activations