© 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. 6882
    Prev
    Next
    INDEX
    Explanations

    flicker / flickr / overflow

    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
    esta
    -0.11
    esser
    -0.09
     hooks
    -0.09
    ื
    -0.09
     tilt
    -0.09
    @js
    -0.08
    ysz
    -0.08
     hamm
    -0.08
    icy
    -0.08
    china
    -0.08
    POSITIVE LOGITS
     flick
    0.21
     lights
    0.17
     candles
    0.15
     Lights
    0.14
    /fl
    0.13
     candle
    0.13
     lighting
    0.11
     eyel
    0.11
    lights
    0.10
     fluorescent
    0.10
    Activations Density 0.006%

    No Known Activations