© 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. 5208
    Prev
    Next
    INDEX
    Explanations

    stated, version, revised

    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
    vido
    -0.10
    ega
    -0.09
     Noon
    -0.09
     imagining
    -0.08
     Franken
    -0.08
    agal
    -0.08
    inel
    -0.08
     Saga
    -0.08
    Ļ¨
    -0.08
     abort
    -0.08
    POSITIVE LOGITS
     addressed
    0.15
     wink
    0.15
     addressing
    0.14
     kissing
    0.13
     whispered
    0.13
     glance
    0.13
    /address
    0.12
     nud
    0.12
     translating
    0.12
     address
    0.12
    Activations Density 0.045%

    No Known Activations