© 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. 15053
    Prev
    Next
    INDEX
    Explanations

    superlatives (clearest, crispest)

    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
    (and
    -0.11
    {}".
    -0.10
     {}'.
    -0.09
     {}".
    -0.09
     thereafter
    -0.09
     bzw
    -0.09
    —and
    -0.08
    ":""
    -0.08
     ().
    -0.08
     %.
    -0.08
    POSITIVE LOGITS
    =?,
    0.18
     {},
    0.17
     _______,
    0.16
    ãĢģ
    0.16
     ?,
    0.16
     -,
    0.15
    ?,
    0.15
    -,
    0.15
    ~,
    0.15
    +,
    0.15
    Activations Density 1.811%

    No Known Activations