© 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. 17689
    Prev
    Next
    INDEX
    Explanations

    roam and wander

    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
     grenades
    -0.11
     Gren
    -0.11
     hurd
    -0.09
    å¾Ħ
    -0.09
    cup
    -0.09
    spe
    -0.09
    hawks
    -0.09
    è´£
    -0.09
    arine
    -0.09
     Coy
    -0.09
    POSITIVE LOGITS
     roam
    0.21
     freely
    0.19
     roaming
    0.18
     streets
    0.18
     around
    0.17
     wander
    0.15
     halls
    0.14
     wandering
    0.14
     wandered
    0.14
     aim
    0.13
    Activations Density 0.040%

    No Known Activations