© 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. 28648
    Prev
    Next
    INDEX
    Explanations

    software licenses and copyright headers

    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
    hints
    -0.09
     reason
    -0.08
     ballo
    -0.08
     Sidney
    -0.08
     dime
    -0.08
     seldom
    -0.08
    izont
    -0.08
    ingo
    -0.08
    ormal
    -0.08
    Pres
    -0.08
    POSITIVE LOGITS
    atee
    0.11
    cid
    0.10
    loc
    0.10
     dara
    0.10
    arse
    0.10
     amph
    0.10
    ales
    0.09
    IBM
    0.09
    ego
    0.09
    alo
    0.09
    Activations Density 0.015%

    No Known Activations