© 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. 4235
    Prev
    Next
    INDEX
    Explanations

    confessions and revelations

    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
     Provid
    -0.13
    cil
    -0.11
    Instr
    -0.09
    /ar
    -0.09
     Cob
    -0.09
     auxiliary
    -0.09
    xia
    -0.09
    ervative
    -0.09
    xx
    -0.09
    /App
    -0.09
    POSITIVE LOGITS
     confession
    0.23
     confess
    0.23
     revelations
    0.19
     disclosures
    0.18
     confessed
    0.17
     about
    0.16
     revealing
    0.16
     reveal
    0.15
     conf
    0.14
     verbally
    0.14
    Activations Density 0.092%

    No Known Activations