© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113770
    Prev
    Next
    INDEX
    Explanations

    black clothing or accessories

    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
     yell
    -0.09
     dark
    -0.09
     colorful
    -0.09
     brown
    -0.09
    iciel
    -0.08
     turquoise
    -0.08
    oji
    -0.08
    alse
    -0.08
     Dark
    -0.08
     yellow
    -0.08
    POSITIVE LOGITS
    ened
    0.13
     Ged
    0.12
     Beaut
    0.11
     widow
    0.10
    -only
    0.10
    nen
    0.10
    Ray
    0.10
    -utils
    0.10
    -on
    0.10
     designer
    0.10
    Activations Density 0.017%

    No Known Activations