© 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. 30108
    Prev
    Next
    INDEX
    Explanations

    this one

    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
    ulle
    -0.10
    Ķ
    -0.10
    arella
    -0.10
     Wend
    -0.09
    ôle
    -0.08
    ird
    -0.08
    ROL
    -0.08
    irl
    -0.08
    adge
    -0.08
    ekt
    -0.08
    POSITIVE LOGITS
     ones
    0.62
     one
    0.50
     Ones
    0.33
    ones
    0.30
    ä¸Ģ
    0.25
    _one
    0.25
    one
    0.24
     particular
    0.22
     ONE
    0.22
     од
    0.21
    Activations Density 0.205%

    No Known Activations