© 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. 49025
    Prev
    Next
    INDEX
    Explanations

    web url paths

    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
    &view
    -0.13
     Accord
    -0.12
     Higgins
    -0.12
    #create
    -0.11
    acco
    -0.11
    .JComboBox
    -0.11
     Maur
    -0.10
    âķĹ
    -0.10
    /category
    -0.10
    <|fim_middle|>
    -0.10
    POSITIVE LOGITS
    ?url
    0.09
    -auto
    0.08
    /Dk
    0.08
    FETCH
    0.07
    1
    0.07
    ?↵↵↵↵
    0.07
     nuclei
    0.07
     Hi
    0.07
     Acad
    0.06
     oath
    0.06
    Activations Density 1.316%

    No Known Activations