© 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. 4210
    Prev
    Next
    INDEX
    Explanations

    Jo 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
    lien
    -0.09
     faulty
    -0.09
    icious
    -0.09
     Horizon
    -0.09
    aurus
    -0.09
    uard
    -0.08
    uous
    -0.08
    rier
    -0.08
    lover
    -0.08
     sworn
    -0.08
    POSITIVE LOGITS
    anne
    0.15
    annes
    0.13
    etta
    0.13
    lette
    0.11
    anmar
    0.10
    jo
    0.10
    ann
    0.10
    quel
    0.10
    annel
    0.10
    Anne
    0.10
    Activations Density 0.008%

    No Known Activations