© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5497
    Prev
    Next
    INDEX
    Explanations

    account, yet, connection

    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
     dislikes
    -0.10
    alous
    -0.09
     consumed
    -0.09
    GD
    -0.09
     steer
    -0.09
    ifu
    -0.09
     bumped
    -0.08
     Trent
    -0.08
    ):-
    -0.08
     renamed
    -0.08
    POSITIVE LOGITS
     yet
    0.13
    nev
    0.12
     Willis
    0.11
     accounts
    0.11
    acz
    0.11
    pak
    0.11
    yet
    0.10
    crate
    0.10
    reate
    0.10
    -account
    0.09
    Activations Density 0.082%

    No Known Activations