© 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. 88332
    Prev
    Next
    INDEX
    Explanations

    ability 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
    lop
    -0.09
    onth
    -0.08
     Rash
    -0.08
     bais
    -0.07
     shar
    -0.07
     Bolt
    -0.07
     attempt
    -0.07
     beh
    -0.07
    ck
    -0.07
     Dro
    -0.07
    POSITIVE LOGITS
     withstand
    0.18
     ability
    0.16
     discern
    0.14
     Ability
    0.14
     adapt
    0.14
    Ability
    0.13
     regenerate
    0.13
    urv
    0.13
     foresee
    0.13
     able
    0.12
    Activations Density 0.168%

    No Known Activations