© 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. 6877
    Prev
    Next
    INDEX
    Explanations

    Âł followed by text

    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
    -0.12
    ynes
    -0.11
     Wahl
    -0.11
    -0.10
     meant
    -0.10
    ³³³
    -0.10
    ippers
    -0.10
    antes
    -0.10
    -0.10
     Wolff
    -0.10
    POSITIVE LOGITS
    ripple
    0.08
     supplied
    0.08
    bage
    0.08
     Hudson
    0.08
    ondo
    0.08
     Vim
    0.08
    DEX
    0.08
    <HTML
    0.08
    /exp
    0.07
     fighter
    0.07
    Activations Density 0.041%

    No Known Activations