© 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. 49482
    Prev
    Next
    INDEX
    Explanations

    sign up or supported

    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
     farther
    -0.08
    ABL
    -0.08
     Tory
    -0.08
     Profit
    -0.08
     eventual
    -0.08
     Bast
    -0.07
    iny
    -0.07
     Turing
    -0.07
     ones
    -0.07
     profits
    -0.07
    POSITIVE LOGITS
     Beau
    0.11
    /connection
    0.10
    	define
    0.10
    erty
    0.10
     fringe
    0.10
     skirt
    0.10
    pto
    0.10
     Tem
    0.10
    PTS
    0.10
    assin
    0.10
    Activations Density 0.001%

    No Known Activations