© 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. 48114
    Prev
    Next
    INDEX
    Explanations

    age indicators

    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
    -plus
    -0.14
    -only
    -0.13
     hatch
    -0.11
    -before
    -0.11
    -headed
    -0.11
    -and
    -0.11
    quoi
    -0.11
    -Feb
    -0.10
     flagship
    -0.10
    acf
    -0.10
    POSITIVE LOGITS
    (s
    0.12
    swith
    0.11
    sss
    0.11
     Caldwell
    0.09
    sto
    0.09
    loads
    0.09
    unde
    0.08
    sWith
    0.08
     sass
    0.08
    ss
    0.08
    Activations Density 0.030%

    No Known Activations