© 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. 111907
    Prev
    Next
    INDEX
    Explanations

    front

    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
     backups
    -0.17
     backup
    -0.16
     Backup
    -0.14
     backed
    -0.14
     backlog
    -0.13
    Backup
    -0.13
    _backup
    -0.13
     backstory
    -0.13
     backpack
    -0.12
     backgrounds
    -0.12
    POSITIVE LOGITS
     foreground
    0.19
     front
    0.17
    foreground
    0.17
    /front
    0.13
     frontend
    0.13
     Front
    0.13
    -front
    0.13
     sides
    0.13
    _front
    0.13
     FRONT
    0.12
    Activations Density 0.099%

    No Known Activations