© 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. 112344
    Prev
    Next
    INDEX
    Explanations

    want to

    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
     vip
    -0.11
    vip
    -0.10
     VIP
    -0.09
     polish
    -0.08
    jest
    -0.08
     BS
    -0.08
    iek
    -0.08
    .hd
    -0.08
     Fuller
    -0.08
    hs
    -0.08
    POSITIVE LOGITS
     obtained
    0.21
     Obt
    0.20
     obtain
    0.19
     obtaining
    0.18
    èİ·åıĸ
    0.17
     obtains
    0.17
     Obtain
    0.15
     obten
    0.15
     obt
    0.14
     acquisition
    0.14
    Activations Density 0.202%

    No Known Activations