© 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. 15634
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    icity
    -0.11
    å°ij
    -0.11
    QR
    -0.11
    zin
    -0.11
    witch
    -0.10
    :no
    -0.10
     бÑĥд
    -0.10
    acet
    -0.10
     weekend
    -0.10
     situación
    -0.10
    POSITIVE LOGITS
     town
    0.08
     effected
    0.08
    ät
    0.07
    croft
    0.06
    nea
    0.06
     pec
    0.06
    ellen
    0.06
     Glover
    0.06
     assembled
    0.06
     Naw
    0.06
    Activations Density 0.070%

    No Known Activations