© 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. 16863
    Prev
    Next
    INDEX
    Explanations

    online Indian

    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
    eba
    -0.14
    uria
    -0.12
    Echo
    -0.11
     PREF
    -0.11
    [$_
    -0.11
    sdale
    -0.11
    faction
    -0.11
    /epl
    -0.11
    lops
    -0.11
    enstein
    -0.11
    POSITIVE LOGITS
     Hud
    0.08
     grat
    0.07
     Grat
    0.07
     confident
    0.07
     confidently
    0.07
    iner
    0.07
     REALLY
    0.07
     Flor
    0.07
    ãĥĪ
    0.07
     gratuitement
    0.07
    Activations Density 0.001%

    No Known Activations