© 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. 15275
    Prev
    Next
    INDEX
    Explanations

    physical positions and actions

    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
    wand
    -0.11
    redi
    -0.11
     dear
    -0.11
    ereg
    -0.10
     stepping
    -0.10
    etch
    -0.10
    stash
    -0.10
     stealth
    -0.10
    pick
    -0.10
     surre
    -0.10
    POSITIVE LOGITS
     Klo
    0.09
     prone
    0.09
     fus
    0.09
    ALK
    0.08
     Kop
    0.08
     face
    0.08
     laughing
    0.08
     crack
    0.08
     blow
    0.08
     IDC
    0.08
    Activations Density 0.020%

    No Known Activations