© 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. 115176
    Prev
    Next
    INDEX
    Explanations

    under the, from the

    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
    ered
    -0.13
    -it
    -0.12
        ↵    ↵    ↵    ↵
    -0.12
    <|fim_suffix|>
    -0.11
    anz
    -0.11
    .the
    -0.11
    stant
    -0.11
    stood
    -0.11
    ycz
    -0.11
     Hib
    -0.11
    POSITIVE LOGITS
    lobal
    0.08
    ycler
    0.07
    anske
    0.06
    elm
    0.06
    {lng
    0.06
     Democr
    0.06
     neighb
    0.05
    lassen
    0.05
    ories
    0.05
     behold
    0.05
    Activations Density 0.278%

    No Known Activations