© 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. 33019
    Prev
    Next
    INDEX
    Explanations

    wrap around

    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
    owl
    -0.08
     tipped
    -0.08
     reckon
    -0.08
    otto
    -0.08
     lodged
    -0.08
    caret
    -0.08
     hack
    -0.08
    oo
    -0.08
     Ot
    -0.08
     literal
    -0.08
    POSITIVE LOGITS
     tightly
    0.21
     tighter
    0.20
     wrapping
    0.17
     wrap
    0.17
     wraps
    0.17
    around
    0.15
     Wrap
    0.15
     tight
    0.15
     unwrap
    0.15
    Around
    0.15
    Activations Density 0.049%

    No Known Activations