© 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. 47211
    Prev
    Next
    INDEX
    Explanations

    being with

    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
     onto
    -0.10
     Zig
    -0.10
     passer
    -0.10
    amage
    -0.10
     Mobil
    -0.10
    zet
    -0.10
     invitations
    -0.10
    utom
    -0.10
    ray
    -0.10
     Abd
    -0.10
    POSITIVE LOGITS
     intimately
    0.16
     physically
    0.12
     romant
    0.12
     closely
    0.10
     together
    0.10
    aye
    0.09
     unprotected
    0.09
    gor
    0.09
     emotionally
    0.09
     outdoors
    0.09
    Activations Density 0.013%

    No Known Activations