© 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. 116958
    Prev
    Next
    INDEX
    Explanations

    refuge, shelter, sanctuary, asylum

    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
    ities
    -0.11
    izzo
    -0.09
     intox
    -0.08
    sters
    -0.08
     immobil
    -0.08
    IPP
    -0.08
     Noon
    -0.08
    nel
    -0.08
    sets
    -0.08
    CAD
    -0.08
    POSITIVE LOGITS
     seeker
    0.12
    ed
    0.12
     seekers
    0.12
    -seeking
    0.11
    /rest
    0.10
    ấ
    0.10
    amu
    0.09
    obel
    0.09
    erb
    0.09
    oba
    0.09
    Activations Density 0.013%

    No Known Activations