© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    direction or side

    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
     complexes
    -0.10
    ippi
    -0.10
     gradu
    -0.10
    ovi
    -0.10
     graduating
    -0.10
     tri
    -0.10
     prio
    -0.10
    voy
    -0.10
     capped
    -0.10
     Hamm
    -0.10
    POSITIVE LOGITS
     directions
    0.14
     direction
    0.12
    ward
    0.09
     Direction
    0.09
    wards
    0.09
     sund
    0.09
     adjust
    0.09
    -direction
    0.09
     bends
    0.08
     toward
    0.08
    Activations Density 0.004%

    No Known Activations