© 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. 32554
    Prev
    Next
    INDEX
    Explanations

    .blogspot/.com

    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
    /Dk
    -0.13
    IFn
    -0.11
    Uvs
    -0.11
    ERSHEY
    -0.11
    Ĺı
    -0.11
     ydk
    -0.10
     democr
    -0.10
     tvb
    -0.10
    	TokenName
    -0.10
     tieten
    -0.10
    POSITIVE LOGITS
    .blogspot
    0.09
    .com
    0.09
     position
    0.07
     appropri
    0.07
    bsp
    0.07
    rement
    0.07
    (ph
    0.07
    @gmail
    0.07
    upt
    0.07
     heb
    0.06
    Activations Density 0.002%

    No Known Activations