© 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. 90722
    Prev
    Next
    INDEX
    Explanations

    important to

    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
    aan
    -0.13
    Tek
    -0.12
     Useful
    -0.12
     Tun
    -0.12
    adro
    -0.12
    spy
    -0.12
    aben
    -0.11
    KEN
    -0.11
     tek
    -0.11
    aren
    -0.11
    POSITIVE LOGITS
     important
    0.20
     importance
    0.19
     Important
    0.18
    important
    0.17
     Importance
    0.17
    Important
    0.16
     mattered
    0.16
    -important
    0.15
     IMPORTANT
    0.14
    IMPORTANT
    0.14
    Activations Density 0.067%

    No Known Activations