© 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. 112737
    Prev
    Next
    INDEX
    Explanations

    end of

    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
    lier
    -0.12
    esen
    -0.12
    lust
    -0.11
    éģĵ
    -0.11
    uria
    -0.11
    lv
    -0.11
    inder
    -0.11
    -minded
    -0.11
     Cot
    -0.11
     posix
    -0.11
    POSITIVE LOGITS
     sticking
    0.10
     stick
    0.09
     ends
    0.09
     end
    0.09
    (end
    0.09
    -end
    0.08
     telescope
    0.08
     Gad
    0.08
     Carol
    0.08
     consum
    0.08
    Activations Density 0.069%

    No Known Activations