© 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. 88822
    Prev
    Next
    INDEX
    Explanations

    community or description

    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
     fray
    -0.13
     midst
    -0.12
     verge
    -0.10
     forefront
    -0.10
     doorstep
    -0.10
     behalf
    -0.10
     myster
    -0.10
     aftermath
    -0.09
    —in
    -0.09
     sidelines
    -0.09
    POSITIVE LOGITS
     motto
    0.12
     nature
    0.12
     demeanor
    0.11
     eyes
    0.10
     muscles
    0.10
     overriding
    0.10
     demean
    0.10
     wasn
    0.10
    ãģ¡ãģ¯
    0.10
    TEL
    0.10
    Activations Density 0.980%

    No Known Activations