© 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. 5049
    Prev
    Next
    INDEX
    Explanations

    describes usage or inclusion

    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
    kar
    -0.09
     Martins
    -0.08
     Bang
    -0.08
     prep
    -0.08
     stal
    -0.08
     Morse
    -0.08
    ambi
    -0.07
    ambient
    -0.07
    elsen
    -0.07
     Mag
    -0.07
    POSITIVE LOGITS
     nonetheless
    0.12
     Luc
    0.12
     nevertheless
    0.11
     otherwise
    0.11
     frankly
    0.10
     Burnett
    0.10
     BOTH
    0.10
     oh
    0.10
     accompanies
    0.10
    æŃ£åľ¨
    0.10
    Activations Density 1.023%

    No Known Activations