© 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. 115214
    Prev
    Next
    INDEX
    Explanations

    I want / I do not

    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
     Rab
    -0.11
    ses
    -0.10
     venir
    -0.10
     Ap
    -0.09
    oner
    -0.09
     redund
    -0.08
    158
    -0.08
    isted
    -0.08
    pv
    -0.08
     gentleman
    -0.08
    POSITIVE LOGITS
     мож
    0.10
    -même
    0.10
    jours
    0.09
    itto
    0.09
     mastur
    0.09
     shalt
    0.09
     wei
    0.09
    otros
    0.09
    venes
    0.09
     pole
    0.09
    Activations Density 0.049%

    No Known Activations