© 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. 116350
    Prev
    Next
    INDEX
    Explanations

    land names or names ending in -ash

    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
    zech
    -0.12
    åĪ¶
    -0.11
    tre
    -0.10
    tatus
    -0.10
    sson
    -0.10
    ascar
    -0.10
    hea
    -0.10
    иÑħ
    -0.10
    isman
    -0.10
    aths
    -0.10
    POSITIVE LOGITS
    (es
    0.31
    mallow
    0.15
    'es
    0.15
    es
    0.15
    ermen
    0.15
    hh
    0.14
    ES
    0.13
    hhh
    0.13
    ers
    0.13
    ness
    0.13
    Activations Density 0.248%

    No Known Activations