© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    freshly / fresh

    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
    ook
    -0.08
    deen
    -0.08
     telephone
    -0.07
    vor
    -0.07
     rough
    -0.07
     Ridge
    -0.07
     sne
    -0.07
    plib
    -0.07
     structured
    -0.07
     Eld
    -0.07
    POSITIVE LOGITS
    -faced
    0.15
    ened
    0.14
    /current
    0.13
    ening
    0.13
    -born
    0.12
    /live
    0.12
     grads
    0.11
    -made
    0.11
    (er
    0.11
    -from
    0.11
    Activations Density 0.007%

    No Known Activations