© 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. 48276
    Prev
    Next
    INDEX
    Explanations

    told [publication/person]

    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
    amine
    -0.09
    anko
    -0.08
     mal
    -0.08
     petitions
    -0.08
    afia
    -0.08
    anks
    -0.08
     ware
    -0.08
     Dro
    -0.08
    ìĦľ
    -0.08
    TES
    -0.08
    POSITIVE LOGITS
     reporters
    0.23
     reporter
    0.18
     me
    0.18
     investigators
    0.16
     interviewer
    0.15
     us
    0.15
     journalists
    0.15
     researchers
    0.15
    Reporter
    0.14
     undercover
    0.13
    Activations Density 0.148%

    No Known Activations