© 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. 26183
    Prev
    Next
    INDEX
    Explanations

    this one

    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
     TBD
    -0.09
    /se
    -0.07
     cohorts
    -0.07
     Typical
    -0.07
    typ
    -0.07
    pek
    -0.07
    coh
    -0.07
    -cluster
    -0.06
    ession
    -0.06
    inh
    -0.06
    POSITIVE LOGITS
     product
    0.21
     item
    0.16
     particular
    0.15
     little
    0.14
     otherwise
    0.14
    product
    0.14
     pricey
    0.13
     hefty
    0.12
     guys
    0.12
     PRODUCT
    0.12
    Activations Density 0.047%

    No Known Activations