© 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. 27747
    Prev
    Next
    INDEX
    Explanations

    someone is responsible

    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
     fel
    -0.10
    cab
    -0.09
    è£
    -0.09
     replay
    -0.09
    Usage
    -0.09
     tys
    -0.08
     íĻ
    -0.08
    osite
    -0.08
     causal
    -0.08
     Favor
    -0.08
    POSITIVE LOGITS
     somebody
    0.40
     someone
    0.39
     Somebody
    0.38
    someone
    0.36
     Someone
    0.36
    Someone
    0.35
     alguien
    0.23
     jemand
    0.18
     responsibility
    0.18
     nobody
    0.18
    Activations Density 0.166%

    No Known Activations