© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 29018
    Prev
    Next
    INDEX
    Explanations

    Ziff, Gifford, wiffle, Griffin, Clifford

    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
    cer
    -0.10
    auer
    -0.09
    er
    -0.09
    iente
    -0.09
    ALLY
    -0.08
     Ri
    -0.08
    >>>>
    -0.08
    sing
    -0.08
    haft
    -0.08
    bul
    -0.08
    POSITIVE LOGITS
    icult
    0.17
    eneg
    0.14
    ault
    0.13
    ord
    0.12
    iculty
    0.12
    els
    0.12
    ed
    0.11
    ERENCE
    0.11
     loft
    0.11
    y
    0.10
    Activations Density 0.021%

    No Known Activations