© 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. 32086
    Prev
    Next
    INDEX
    Explanations

    are here:

    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
    illery
    -0.06
    pson
    -0.06
    Âł
    -0.06
     goof
    -0.06
    etheless
    -0.06
     \"$
    -0.05
    Muon
    -0.05
     MLM
    -0.05
    venture
    -0.05
    [âĢ¦
    -0.05
    POSITIVE LOGITS
    /libs
    0.14
    MaxLength
    0.13
    IPP
    0.13
     nums
    0.12
    ETERS
    0.12
    !/
    0.12
    /python
    0.12
    pra
    0.12
    [](
    0.12
    Sent
    0.12
    Activations Density 0.757%

    No Known Activations