© 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. 49456
    Prev
    Next
    INDEX
    Explanations

    abs or Abs followed by specific endings

    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
     Gilles
    -0.12
    illes
    -0.08
    sgiving
    -0.08
     Doub
    -0.08
    gis
    -0.08
    ship
    -0.08
    ificate
    -0.08
     rusty
    -0.08
     buckle
    -0.08
    undy
    -0.08
    POSITIVE LOGITS
     abs
    0.25
     Abs
    0.23
    Abs
    0.21
     absor
    0.20
     absorption
    0.19
    abs
    0.19
    -abs
    0.18
     absorbed
    0.18
    .Abs
    0.17
     absorbs
    0.17
    Activations Density 0.010%

    No Known Activations