© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88150
    Prev
    Next
    INDEX
    Explanations

    bringing forth spirits, images, action

    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
    emit
    -0.10
    Hooks
    -0.09
     stride
    -0.09
     ensl
    -0.09
     induction
    -0.09
     wink
    -0.09
    cha
    -0.08
     strain
    -0.08
    ondo
    -0.08
     cracks
    -0.08
    POSITIVE LOGITS
     spirits
    0.19
     memories
    0.14
     images
    0.14
     spirit
    0.14
     demons
    0.13
     forth
    0.12
     Spirits
    0.12
     ghosts
    0.12
     spect
    0.12
     genie
    0.12
    Activations Density 0.116%

    No Known Activations