© 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. 89056
    Prev
    Next
    INDEX
    Explanations

    Benjamin, Hein, person names

    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
     Mega
    -0.09
    anco
    -0.09
    thin
    -0.09
    anic
    -0.09
    ties
    -0.09
    anter
    -0.09
     plac
    -0.09
    oner
    -0.09
    auce
    -0.09
    anz
    -0.09
    POSITIVE LOGITS
    sav
    0.09
     squeez
    0.09
    rich
    0.09
     grasp
    0.09
    reich
    0.09
    etta
    0.09
    steen
    0.09
     Klaus
    0.09
    Absolute
    0.09
     Absolute
    0.08
    Activations Density 0.026%

    No Known Activations