© 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. 25411
    Prev
    Next
    INDEX
    Explanations

    weekend getaway

    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
     beings
    -0.11
    izz
    -0.08
     Vik
    -0.08
    esse
    -0.08
    ances
    -0.08
     misguided
    -0.08
    Haunted
    -0.08
    arias
    -0.08
    ugi
    -0.08
     åĬ
    -0.08
    POSITIVE LOGITS
    -long
    0.17
     retreat
    0.13
    -length
    0.12
    -after
    0.11
     getaway
    0.11
    /month
    0.10
     rendez
    0.10
    /temp
    0.10
    awy
    0.10
    avis
    0.10
    Activations Density 0.008%

    No Known Activations