© 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. 88513
    Prev
    Next
    INDEX
    Explanations

    gone, disappeared, removed, sold out

    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
     surroundings
    -0.09
    ovi
    -0.09
     lud
    -0.07
     cousins
    -0.07
     united
    -0.07
     serr
    -0.07
     areas
    -0.07
    esa
    -0.06
    esch
    -0.06
    DFS
    -0.06
    POSITIVE LOGITS
     disappeared
    0.14
     disappears
    0.13
     disappear
    0.13
     disappe
    0.11
    rvine
    0.11
     trad
    0.11
    #aa
    0.11
     Gone
    0.11
     disappearing
    0.11
    ît
    0.11
    Activations Density 0.001%

    No Known Activations