© 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. 4418
    Prev
    Next
    INDEX
    Explanations

    states of confidence or vulnerability

    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
     whatsoever
    -0.11
     Cra
    -0.10
     anew
    -0.10
     Zw
    -0.09
    esso
    -0.09
    ~-
    -0.09
     sofort
    -0.09
     differently
    -0.09
    right
    -0.09
     detail
    -0.09
    POSITIVE LOGITS
     cadre
    0.10
    thon
    0.10
    ÑģÑı
    0.10
     ones
    0.09
     dise
    0.09
     pel
    0.09
     Shelby
    0.08
    okes
    0.08
    lr
    0.08
    <|fim_suffix|>
    0.08
    Activations Density 0.175%

    No Known Activations