© 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. 17151
    Prev
    Next
    INDEX
    Explanations

    places or activities followed by description

    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
     sogar
    -0.10
    _pref
    -0.09
     furthermore
    -0.08
     unsuccessfully
    -0.08
    raj
    -0.08
    verb
    -0.08
    804
    -0.08
     fantas
    -0.08
     even
    -0.08
     penned
    -0.08
    POSITIVE LOGITS
     consists
    0.25
     consist
    0.24
     consisted
    0.24
     resembled
    0.13
     smells
    0.13
     smelled
    0.13
     contains
    0.13
     seemed
    0.12
     differed
    0.12
     comprises
    0.12
    Activations Density 0.090%

    No Known Activations