© 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. 28710
    Prev
    Next
    INDEX
    Explanations

    copyright notices and dates

    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
     Boh
    -0.11
    adro
    -0.10
    olla
    -0.10
    bara
    -0.10
    vro
    -0.10
     Fin
    -0.09
    metro
    -0.09
     Top
    -0.09
    vla
    -0.09
     toler
    -0.09
    POSITIVE LOGITS
     dripping
    0.09
     SignUp
    0.08
     Hardcore
    0.08
     incidental
    0.08
     Forbidden
    0.08
     Minds
    0.08
     negotiated
    0.08
     Bend
    0.08
     dis
    0.08
     metaph
    0.08
    Activations Density 0.682%

    No Known Activations