© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48783
    Prev
    Next
    INDEX
    Explanations

    sleep and sleeping

    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
    oner
    -0.11
    onne
    -0.10
    plete
    -0.10
     lif
    -0.09
    allon
    -0.09
     livest
    -0.09
    olle
    -0.09
    ondon
    -0.09
    ities
    -0.08
    pres
    -0.08
    POSITIVE LOGITS
    iness
    0.14
    walking
    0.14
    mans
    0.13
    /rest
    0.13
    ers
    0.11
    ÂŃing
    0.11
     deprivation
    0.11
    scape
    0.11
    wear
    0.10
    walker
    0.10
    Activations Density 0.021%

    No Known Activations