© 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. 17512
    Prev
    Next
    INDEX
    Explanations

    addressing someone

    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
     specialized
    -0.07
    ...↵
    -0.07
    ,
    -0.07
     Bliss
    -0.07
    Called
    -0.07
    ...,
    -0.07
    ...↵↵
    -0.07
    str
    -0.07
    nl
    -0.06
    !
    -0.06
    POSITIVE LOGITS
     dear
    0.16
     indeb
    0.15
     arsch
    0.14
     hmm
    0.13
     putas
    0.13
     huh
    0.12
     especially
    0.12
     anyway
    0.12
     gentlemen
    0.12
     mio
    0.12
    Activations Density 0.009%

    No Known Activations