© 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. 7509
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
     paternal
    -0.11
     UNIVERS
    -0.11
     stro
    -0.10
    dana
    -0.10
     dici
    -0.10
    Univers
    -0.10
    dsp
    -0.10
     Misc
    -0.10
    pes
    -0.10
     novice
    -0.10
    POSITIVE LOGITS
     dot
    0.08
     segmented
    0.07
     followed
    0.07
     Afr
    0.07
     Wolfe
    0.07
     Mothers
    0.07
     crippling
    0.07
     cracked
    0.07
    YPE
    0.07
    675
    0.07
    Activations Density 0.052%

    No Known Activations