© 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. 48560
    Prev
    Next
    INDEX
    Explanations

    IIoppoloI18NIñigoIidaI.P.ICRItoIstitutoIEDMIphone

    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
    -0.17
    ’re
    -0.17
    aven
    -0.11
    aler
    -0.10
    rne
    -0.09
    inz
    -0.09
    bsites
    -0.09
    isman
    -0.09
    ilk
    -0.09
    my
    -0.08
    POSITIVE LOGITS
    cel
    0.11
    lluminate
    0.11
     mean
    0.11
     vests
    0.10
    WO
    0.10
     seams
    0.10
     Beaver
    0.10
     ME
    0.10
    .mean
    0.10
     vant
    0.09
    Activations Density 0.394%

    No Known Activations