© 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. 47142
    Prev
    Next
    INDEX
    Explanations

    Urs, Thor, elle

    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
    otron
    -0.08
     &,
    -0.07
    ACS
    -0.07
    602
    -0.07
     INST
    -0.07
    ,[],
    -0.07
     alm
    -0.07
    ICT
    -0.07
     {},
    -0.07
     Sidebar
    -0.07
    POSITIVE LOGITS
    ::*
    0.11
     Eg
    0.10
    woo
    0.10
    Expose
    0.10
    quine
    0.10
    _Core
    0.09
    /details
    0.09
    <|endoftext|>
    0.09
    ası
    0.09
    /png
    0.09
    Activations Density 0.025%

    No Known Activations