© 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. 90801
    Prev
    Next
    INDEX
    Explanations

    fading memories

    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
     unheard
    -0.12
     unseen
    -0.09
     historical
    -0.09
     Ãľ
    -0.09
     rigged
    -0.09
     dummy
    -0.09
     historic
    -0.09
     Invisible
    -0.09
    .ud
    -0.08
    histor
    -0.08
    POSITIVE LOGITS
     vivid
    0.16
     fade
    0.16
     cherished
    0.15
     faded
    0.15
     fading
    0.15
     fond
    0.14
     cherish
    0.14
     Fade
    0.13
     fades
    0.13
     fragment
    0.13
    Activations Density 0.062%

    No Known Activations