© 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. 15129
    Prev
    Next
    INDEX
    Explanations

    provided by a third party

    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
    izzo
    -0.12
    visor
    -0.12
    @js
    -0.12
    -ca
    -0.11
    ingo
    -0.11
     voc
    -0.11
    )did
    -0.11
    Tv
    -0.11
    rightness
    -0.10
    opr
    -0.10
    POSITIVE LOGITS
    iba
    0.09
     Pf
    0.09
     gala
    0.09
     cater
    0.08
     rou
    0.08
    alia
    0.08
    Pad
    0.07
    ëŁ
    0.07
    holm
    0.07
    oya
    0.07
    Activations Density 0.002%

    No Known Activations