© 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. 90267
    Prev
    Next
    INDEX
    Explanations

    secret and disclosure

    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
     Gilles
    -0.13
    ged
    -0.12
     Straw
    -0.11
    alyzed
    -0.10
     minded
    -0.10
    åĮĸ
    -0.10
     ged
    -0.10
    stra
    -0.10
    .gs
    -0.10
    ouver
    -0.10
    POSITIVE LOGITS
     marvel
    0.10
     wink
    0.09
    (secret
    0.08
     tut
    0.08
    rend
    0.08
     tip
    0.08
     harb
    0.08
    urn
    0.08
     pcb
    0.08
    /admin
    0.07
    Activations Density 0.016%

    No Known Activations