© 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. 49657
    Prev
    Next
    INDEX
    Explanations

    j names and sequences

    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
    aes
    -0.11
    aN
    -0.09
    a
    -0.08
    aos
    -0.08
    ERM
    -0.08
    à¸ĵ
    -0.08
    ucci
    -0.08
    ÑĢи
    -0.08
    OWN
    -0.07
    complete
    -0.07
    POSITIVE LOGITS
    ournals
    0.17
    ection
    0.17
    unct
    0.16
    ournal
    0.16
    ee
    0.15
    ackson
    0.15
    eb
    0.15
    eba
    0.14
    oints
    0.14
    itsu
    0.13
    Activations Density 0.342%

    No Known Activations