© 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. 46883
    Prev
    Next
    INDEX
    Explanations

    language codes

    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
     mur
    -0.08
    ily
    -0.07
     summ
    -0.07
     socks
    -0.07
     hass
    -0.07
    aton
    -0.07
    /lic
    -0.07
     peri
    -0.07
     overhead
    -0.07
    plet
    -0.06
    POSITIVE LOGITS
     Anc
    0.12
     Greenwood
    0.11
     Antique
    0.11
     ][
    0.11
     Stam
    0.10
    rove
    0.10
     âĢķ
    0.10
     Nested
    0.10
     Dann
    0.10
    ensis
    0.10
    Activations Density 0.002%

    No Known Activations