© 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. 14408
    Prev
    Next
    INDEX
    Explanations

    password and login

    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
    artin
    -0.11
    fcc
    -0.10
    edis
    -0.10
    ToStr
    -0.10
     Denied
    -0.10
     Trevor
    -0.10
     Blocked
    -0.10
     haber
    -0.10
     travers
    -0.10
     perme
    -0.10
    POSITIVE LOGITS
    /bind
    0.09
    itsu
    0.08
     twin
    0.08
     swiftly
    0.08
    appa
    0.08
    Cod
    0.08
     Credential
    0.08
     Calder
    0.08
     shortcut
    0.07
    imoto
    0.07
    Activations Density 0.005%

    No Known Activations