© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 14659
    Prev
    Next
    INDEX
    Explanations

    hunting and sport

    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
     Skate
    -0.11
     nom
    -0.11
     scav
    -0.11
     Buccane
    -0.11
     Nom
    -0.11
     Pil
    -0.10
     crews
    -0.10
     Wander
    -0.10
    Nom
    -0.10
    @stop
    -0.10
    POSITIVE LOGITS
     shooting
    0.12
     brag
    0.10
     trophy
    0.10
     rifles
    0.10
     leased
    0.10
     ast
    0.10
     Trophy
    0.09
     deco
    0.09
     avid
    0.09
     game
    0.09
    Activations Density 0.153%

    No Known Activations