© 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. 114172
    Prev
    Next
    INDEX
    Explanations

    anything or nothing

    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
    -corner
    -0.08
    afort
    -0.08
     utmost
    -0.08
     Shea
    -0.08
    falls
    -0.08
    ses
    -0.08
    (er
    -0.08
     oe
    -0.08
     мож
    -0.08
    urses
    -0.07
    POSITIVE LOGITS
     resembling
    0.19
     except
    0.15
     reminiscent
    0.13
     beyond
    0.12
    isel
    0.12
     besides
    0.12
     remotely
    0.12
    except
    0.12
     Except
    0.11
     akin
    0.11
    Activations Density 0.031%

    No Known Activations