© 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. 15824
    Prev
    Next
    INDEX
    Explanations

    Winter War, Special, Wedding, berg, fest, games

    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
     Chop
    -0.11
    inator
    -0.10
    eres
    -0.10
     Fres
    -0.10
     Trent
    -0.09
     summers
    -0.09
    änge
    -0.09
    dT
    -0.09
     summer
    -0.09
    abin
    -0.09
    POSITIVE LOGITS
    mute
    0.16
    werp
    0.14
    thur
    0.12
    bourne
    0.11
    green
    0.11
    /s
    0.11
    semester
    0.10
     Wonderland
    0.10
    steller
    0.10
     Proud
    0.10
    Activations Density 0.025%

    No Known Activations