© 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. 116372
    Prev
    Next
    INDEX
    Explanations

    emerging from darkness or hiding places

    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
     Gong
    -0.11
     Ook
    -0.10
    uo
    -0.10
    uft
    -0.10
    PCM
    -0.09
     awake
    -0.09
    TRS
    -0.09
    %d
    -0.09
    ÑĮÑİ
    -0.09
    PIO
    -0.09
    POSITIVE LOGITS
     nowhere
    0.19
     shadows
    0.15
     hiding
    0.15
     bushes
    0.12
     darkness
    0.12
     depths
    0.12
     conceal
    0.11
     somewhere
    0.11
     apparently
    0.10
     seemingly
    0.10
    Activations Density 0.084%

    No Known Activations