© 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. 4770
    Prev
    Next
    INDEX
    Explanations

    word followed by punctuation

    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
     Griff
    -0.08
     âĢ¦↵↵
    -0.08
     Scient
    -0.07
     delet
    -0.07
     FIL
    -0.07
     ↵
    -0.07
     convers
    -0.07
     Dolphin
    -0.07
     Baths
    -0.07
     ï
    -0.07
    POSITIVE LOGITS
     Archives
    0.12
    reh
    0.11
    bru
    0.11
    ·
    0.11
    riot
    0.11
    _flutter
    0.10
    /o
    0.10
    clar
    0.10
    @media
    0.10
    sono
    0.10
    Activations Density 0.230%

    No Known Activations