© 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. 31185
    Prev
    Next
    INDEX
    Explanations

    access points and exits

    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
     ration
    -0.09
     hog
    -0.09
    reo
    -0.09
    loh
    -0.08
     Hayden
    -0.08
    iste
    -0.08
    libs
    -0.08
    /id
    -0.08
     exert
    -0.08
    Offline
    -0.08
    POSITIVE LOGITS
     exit
    0.32
     entrance
    0.30
     entrances
    0.30
     exits
    0.29
     Entrance
    0.27
     Exit
    0.25
     ingress
    0.25
     access
    0.25
    Exit
    0.24
    exit
    0.24
    Activations Density 0.445%

    No Known Activations