© 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. 90174
    Prev
    Next
    INDEX
    Explanations

    projectiles and shooting

    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
     bliss
    -0.10
     hood
    -0.10
     padded
    -0.09
    ulg
    -0.09
     slack
    -0.09
     SEEK
    -0.08
     eup
    -0.08
    lia
    -0.08
    rik
    -0.08
     gyr
    -0.08
    POSITIVE LOGITS
     spit
    0.19
     discharge
    0.18
     ejac
    0.17
     Ej
    0.17
     shoot
    0.17
     firing
    0.16
     Spit
    0.16
     projectiles
    0.16
     fire
    0.16
     shooting
    0.16
    Activations Density 0.117%

    No Known Activations