© 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. 26533
    Prev
    Next
    INDEX
    Explanations

    the [noun phrase]

    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
    owa
    -0.10
    .easy
    -0.09
    achs
    -0.09
    ,");↵
    -0.09
    atas
    -0.09
    à¸ĸ
    -0.09
    agli
    -0.09
    ison
    -0.09
    ]|[
    -0.09
    dorf
    -0.08
    POSITIVE LOGITS
     havoc
    0.17
     things
    0.15
     way
    0.13
     ways
    0.13
     hoops
    0.12
     concessions
    0.11
     sacrifices
    0.11
     favors
    0.11
     manner
    0.11
     amount
    0.11
    Activations Density 0.665%

    No Known Activations