© 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. 4915
    Prev
    Next
    INDEX
    Explanations

    Beck related names and depression inventories

    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
    unsch
    -0.11
    tery
    -0.10
     Esk
    -0.10
    rien
    -0.09
    zburg
    -0.09
    hawks
    -0.09
    _subtype
    -0.09
    resher
    -0.09
    zd
    -0.09
     pseudo
    -0.09
    POSITIVE LOGITS
    oning
    0.12
    eba
    0.11
    WITH
    0.11
    loff
    0.10
     Depression
    0.10
    oned
    0.09
     ener
    0.09
    with
    0.09
    ers
    0.09
    âĶģ
    0.09
    Activations Density 0.013%

    No Known Activations