© 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. 15567
    Prev
    Next
    INDEX
    Explanations

    does anyone know

    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
    ship
    -0.10
    zell
    -0.10
    ÑĥÑĤ
    -0.09
     Holl
    -0.09
    illard
    -0.09
    /false
    -0.09
    shi
    -0.09
    shine
    -0.09
    ÑĨа
    -0.09
    Ø´
    -0.09
    POSITIVE LOGITS
     anyone
    0.16
     anybody
    0.15
    NotExist
    0.12
     wonders
    0.10
     Anyone
    0.10
    Anyone
    0.09
    nt
    0.09
    444
    0.08
    able
    0.08
    mere
    0.08
    Activations Density 0.012%

    No Known Activations