© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    what specifically

    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
    macros
    -0.10
    nore
    -0.10
    åķĨ
    -0.10
    urn
    -0.10
    eki
    -0.10
    IPS
    -0.10
    emd
    -0.10
     shredd
    -0.09
    Debugger
    -0.09
     aprove
    -0.09
    POSITIVE LOGITS
     specifically
    0.13
     specifics
    0.12
    åħ·
    0.12
     exactly
    0.12
     Specifically
    0.12
    Specific
    0.10
     Ord
    0.09
     particulars
    0.09
     allege
    0.09
    specific
    0.09
    Activations Density 0.067%

    No Known Activations