© 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. 3758
    Prev
    Next
    INDEX
    Explanations

    challenging conventions or assumptions

    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
     Tome
    -0.11
    rams
    -0.10
    nof
    -0.10
    -as
    -0.10
    -gap
    -0.10
    etto
    -0.10
     diss
    -0.10
    zag
    -0.10
     Ruf
    -0.10
     drift
    -0.10
    POSITIVE LOGITS
     conventional
    0.12
     notions
    0.11
     assumptions
    0.11
     simplistic
    0.10
     conventions
    0.10
     ideal
    0.09
     gim
    0.09
     moral
    0.08
     definitions
    0.08
     Stark
    0.08
    Activations Density 0.001%

    No Known Activations