© 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. 26185
    Prev
    Next
    INDEX
    Explanations

    wander or stumble

    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
     halfway
    -0.10
     ordered
    -0.09
     ceremon
    -0.09
     Dop
    -0.09
    ynes
    -0.08
     shaving
    -0.08
     intimately
    -0.08
    hof
    -0.08
     dob
    -0.08
    perf
    -0.08
    POSITIVE LOGITS
     wandered
    0.17
     wander
    0.16
     wandering
    0.16
     scav
    0.14
     cautiously
    0.14
     wand
    0.14
     Wander
    0.14
     Nearby
    0.13
     stumbled
    0.13
     stumbling
    0.13
    Activations Density 0.063%

    No Known Activations