© 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. 32715
    Prev
    Next
    INDEX
    Explanations

    "A:" or ":" followed by text

    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
    vana
    -0.08
    borg
    -0.08
    dek
    -0.08
    cheid
    -0.07
     Chandler
    -0.07
     Transitional
    -0.07
    opi
    -0.07
     transitional
    -0.07
    inky
    -0.07
    colo
    -0.07
    POSITIVE LOGITS
     Beitrag
    0.11
     doub
    0.11
     dash
    0.10
    angen
    0.10
    ices
    0.10
    ration
    0.10
     deb
    0.10
    ange
    0.10
    actics
    0.10
     pard
    0.10
    Activations Density 0.015%

    No Known Activations