© 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. 114734
    Prev
    Next
    INDEX
    Explanations

    shadow words

    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
     dicks
    -0.11
     boys
    -0.11
     Balls
    -0.10
     booty
    -0.10
     Buf
    -0.09
     abbreviation
    -0.09
     Soccer
    -0.09
     dudes
    -0.09
     Rocks
    -0.09
     Dude
    -0.09
    POSITIVE LOGITS
    shadow
    0.15
     shadow
    0.15
     Raven
    0.15
     Shadows
    0.14
    Shadow
    0.13
     twilight
    0.13
    .shadow
    0.13
     shadows
    0.13
     phoenix
    0.13
    _shadow
    0.13
    Activations Density 0.056%

    No Known Activations