© 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. 92070
    Prev
    Next
    INDEX
    Explanations

    apache license

    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
    alse
    -0.13
    tru
    -0.12
    >čč↵
    -0.12
    ersed
    -0.11
    _ALIAS
    -0.10
    zl
    -0.10
     ig
    -0.10
    velle
    -0.10
     iq
    -0.10
    UNK
    -0.10
    POSITIVE LOGITS
     possibilities
    0.07
     Achilles
    0.07
     hab
    0.07
    Magic
    0.07
     convert
    0.06
    úb
    0.06
     (...
    0.06
     fun
    0.06
    ÅĽci
    0.06
     experience
    0.06
    Activations Density 0.001%

    No Known Activations