© 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. 18253
    Prev
    Next
    INDEX
    Explanations

    web links and questions

    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
     Heller
    -0.08
    KM
    -0.08
     GOT
    -0.08
     st
    -0.07
     IM
    -0.07
     Barn
    -0.07
     clap
    -0.07
    unction
    -0.07
    NECT
    -0.07
    andle
    -0.07
    POSITIVE LOGITS
     ging
    0.13
     leaning
    0.12
     leaned
    0.12
     lenght
    0.11
    âĺħ
    0.11
     refr
    0.11
     Went
    0.10
    orny
    0.10
     waive
    0.10
    [âĢ¦]
    0.10
    Activations Density 0.149%

    No Known Activations