© 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. 50298
    Prev
    Next
    INDEX
    Explanations

    family names

    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
     handy
    -0.08
    hores
    -0.08
    /license
    -0.07
    obsolete
    -0.07
    upt
    -0.07
     Moff
    -0.07
    esi
    -0.06
     ninete
    -0.06
    çĽijåIJ¬é¡µéĿ¢
    -0.06
     Composer
    -0.06
    POSITIVE LOGITS
    's
    0.20
    -led
    0.18
    ’s
    0.16
    -centric
    0.16
    -authored
    0.16
    isms
    0.15
    -centered
    0.15
    `s
    0.15
     fans
    0.14
     solo
    0.14
    Activations Density 0.487%

    No Known Activations