© 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. 113354
    Prev
    Next
    INDEX
    Explanations

    scenes of action and violence

    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
     unknow
    -0.10
     Manhattan
    -0.09
     prep
    -0.09
    iaux
    -0.08
     unused
    -0.08
     rods
    -0.08
     Blues
    -0.08
     facet
    -0.08
     uniquely
    -0.08
    fac
    -0.07
    POSITIVE LOGITS
     scenes
    0.20
     inters
    0.17
     Scenes
    0.17
     sequences
    0.16
    -scenes
    0.15
    scenes
    0.14
     pepper
    0.14
    /action
    0.14
     plentiful
    0.13
     sprink
    0.13
    Activations Density 0.088%

    No Known Activations