© 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. 14884
    Prev
    Next
    INDEX
    Explanations

    end or endpoint

    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
     Crow
    -0.10
     tilted
    -0.10
     crow
    -0.10
     Entr
    -0.10
    utan
    -0.10
    olan
    -0.10
     rocking
    -0.10
     Hund
    -0.09
     Rut
    -0.09
    uner
    -0.09
    POSITIVE LOGITS
     ends
    0.22
     end
    0.19
     Ends
    0.19
     endpoints
    0.17
     length
    0.16
     Length
    0.16
    端
    0.15
     endpoint
    0.15
    -end
    0.14
    Length
    0.14
    Activations Density 0.617%

    No Known Activations