© 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. 46410
    Prev
    Next
    INDEX
    Explanations

    Microsoft products and development tools

    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
     Saul
    -0.08
     Åĵ
    -0.08
     Dow
    -0.08
    agu
    -0.08
    ioxide
    -0.08
    lijah
    -0.07
     demo
    -0.07
     PTS
    -0.07
     Zwe
    -0.07
    esi
    -0.07
    POSITIVE LOGITS
     preocup
    0.10
    /end
    0.10
    uko
    0.10
     fas
    0.10
    rene
    0.10
    Я
    0.10
    ë¶Ħ
    0.10
    iv
    0.10
    Ut
    0.10
    rum
    0.10
    Activations Density 0.002%

    No Known Activations