© 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. 46523
    Prev
    Next
    INDEX
    Explanations

    2go or 2image

    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
     nominal
    -0.09
    -ish
    -0.08
    -quarters
    -0.08
     sig
    -0.08
    fold
    -0.07
     Fou
    -0.07
    arg
    -0.07
     brav
    -0.07
    issen
    -0.07
    -five
    -0.07
    POSITIVE LOGITS
    gether
    0.18
    nds
    0.13
    nd
    0.12
    trib
    0.12
    go
    0.12
    ombs
    0.11
    orrow
    0.11
     nowhere
    0.11
    preci
    0.11
     Fist
    0.11
    Activations Density 0.119%

    No Known Activations