© 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. 113990
    Prev
    Next
    INDEX
    Explanations

    what is leftover

    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
     grate
    -0.09
     redis
    -0.07
     some
    -0.07
    ensi
    -0.07
    ankan
    -0.07
    ++
    -0.06
    +++
    -0.06
     kinda
    -0.06
    asion
    -0.06
    997
    -0.06
    POSITIVE LOGITS
     remaining
    0.17
     spare
    0.16
     few
    0.15
     ÑĥÑģп
    0.14
     remained
    0.14
    remaining
    0.13
     Remaining
    0.13
     portions
    0.13
    оÑĩ
    0.13
     bits
    0.12
    Activations Density 0.112%

    No Known Activations