© 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. 5280
    Prev
    Next
    INDEX
    Explanations

    you told me so

    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
     conced
    -0.11
    ...',↵
    -0.10
     fals
    -0.09
    -↵↵
    -0.09
    /loading
    -0.09
    YL
    -0.09
    ...",↵
    -0.09
     Needless
    -0.09
     Suff
    -0.09
    soever
    -0.09
    POSITIVE LOGITS
    ?
    0.10
    bens
    0.09
     warranted
    0.09
     fanc
    0.09
     nuts
    0.09
    innie
    0.09
     easy
    0.08
    iw
    0.08
     enr
    0.08
    eger
    0.08
    Activations Density 0.005%

    No Known Activations