© 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. 89110
    Prev
    Next
    INDEX
    Explanations

    sunglasses and/

    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
     glass
    -0.20
     Glass
    -0.19
     glasses
    -0.19
    glass
    -0.18
     Glasses
    -0.17
    Glass
    -0.16
     Glasgow
    -0.13
     Glas
    -0.13
     transparency
    -0.12
    allas
    -0.11
    POSITIVE LOGITS
    arda
    0.09
     throat
    0.08
     mk
    0.08
    ervo
    0.08
    dia
    0.08
     hairy
    0.08
    addy
    0.07
     Ced
    0.07
    indice
    0.07
    erval
    0.07
    Activations Density 0.032%

    No Known Activations