© 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. 49853
    Prev
    Next
    INDEX
    Explanations

    defense against

    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
    .TryParse
    -0.15
    noinspection
    -0.14
    .myapplication
    -0.13
    lessly
    -0.12
    -eyed
    -0.12
    -less
    -0.12
     tslint
    -0.12
    theless
    -0.12
    izontal
    -0.12
    ÑģÑı
    -0.11
    POSITIVE LOGITS
    (er
    0.09
     (()
    0.07
    ardash
    0.07
    ERV
    0.06
    bef
    0.06
    yps
    0.06
    (Runtime
    0.05
    ÄĻd
    0.05
    cff
    0.05
     *,↵
    0.05
    Activations Density 23.909%

    No Known Activations