© 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. 25862
    Prev
    Next
    INDEX
    Explanations

    where things are located

    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
    miss
    -0.10
    aldo
    -0.10
    yh
    -0.10
     sendo
    -0.10
     Haley
    -0.10
    hk
    -0.10
     benef
    -0.10
    anko
    -0.10
    ãģ¯
    -0.10
     Natal
    -0.09
    POSITIVE LOGITS
     resides
    0.24
     reside
    0.21
     lives
    0.16
     exists
    0.15
     operates
    0.14
     occurs
    0.13
     originated
    0.12
     lies
    0.12
     originates
    0.12
     awaits
    0.11
    Activations Density 0.135%

    No Known Activations