© 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. 18150
    Prev
    Next
    INDEX
    Explanations

    my followed by a noun

    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
    're
    -0.09
    dio
    -0.09
    ibal
    -0.08
    etical
    -0.08
    enton
    -0.08
    BERT
    -0.08
    esk
    -0.08
    们
    -0.08
    bert
    -0.08
     Cong
    -0.08
    POSITIVE LOGITS
    rtle
    0.25
     myself
    0.25
    croft
    0.22
    riad
    0.21
    opic
    0.20
    /my
    0.20
    opia
    0.17
    anmar
    0.17
    ri
    0.16
    ths
    0.16
    Activations Density 0.172%

    No Known Activations