© 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. 7372
    Prev
    Next
    INDEX
    Explanations

    ; it license

    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
     wides
    -0.08
     foul
    -0.08
     Conte
    -0.08
     invite
    -0.08
    omo
    -0.08
     invites
    -0.08
     Faul
    -0.08
     Tage
    -0.07
     incumb
    -0.07
    Creature
    -0.07
    POSITIVE LOGITS
    -death
    0.11
     Strand
    0.11
    rox
    0.10
     Diss
    0.10
     death
    0.10
     Canc
    0.10
    :↵
    0.10
    oton
    0.10
    boost
    0.09
     frankly
    0.09
    Activations Density 0.001%

    No Known Activations