© 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. 31526
    Prev
    Next
    INDEX
    Explanations

    old / old school / fashioned

    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
     cent
    -0.12
    emple
    -0.09
     needless
    -0.09
     Bans
    -0.09
     Burr
    -0.09
     Hamm
    -0.09
    zan
    -0.09
     SCAN
    -0.09
    egg
    -0.09
     Nath
    -0.09
    POSITIVE LOGITS
    -fashioned
    0.15
     fashioned
    0.13
    -school
    0.10
     enough
    0.10
    -old
    0.10
     compared
    0.10
     Spread
    0.10
     undergrad
    0.09
    Ú¯
    0.09
    (er
    0.09
    Activations Density 0.011%

    No Known Activations