© 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. 113927
    Prev
    Next
    INDEX
    Explanations

    time stamps with zone

    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
     lifts
    -0.12
    Uploader
    -0.11
    aud
    -0.10
    adas
    -0.10
    DDL
    -0.10
     ghost
    -0.10
     lifting
    -0.10
    rient
    -0.10
    /bar
    -0.10
     Lift
    -0.10
    POSITIVE LOGITS
     gri
    0.09
     Kro
    0.09
     Moo
    0.08
     incor
    0.08
     paras
    0.07
     gul
    0.07
     interracial
    0.07
     Pell
    0.07
     Marg
    0.07
     Ruf
    0.07
    Activations Density 0.001%

    No Known Activations