© 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. 111954
    Prev
    Next
    INDEX
    Explanations

    mobile app development

    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
    ì¹ĺ
    -0.12
     fam
    -0.11
    TPL
    -0.11
    undry
    -0.10
     madre
    -0.10
     indeb
    -0.10
     amore
    -0.10
    SSFWorkbook
    -0.10
     ami
    -0.10
     forks
    -0.09
    POSITIVE LOGITS
     Mobile
    0.13
    Mobile
    0.12
     Mob
    0.11
     mobile
    0.11
     mob
    0.10
    .Mobile
    0.09
    .Comp
    0.09
     Tablet
    0.08
     Mobility
    0.08
     mobility
    0.08
    Activations Density 0.211%

    No Known Activations