© 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. 7144
    Prev
    Next
    INDEX
    Explanations

    things and stuff

    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
     seri
    -0.12
    blk
    -0.12
    elay
    -0.11
    IQ
    -0.11
     naï
    -0.11
     blk
    -0.10
     gag
    -0.10
     joking
    -0.10
    alley
    -0.10
     handic
    -0.10
    POSITIVE LOGITS
     stuff
    0.24
    ness
    0.21
     goodness
    0.20
     Stuff
    0.20
    stuff
    0.19
    _stuff
    0.18
     things
    0.18
    Stuff
    0.18
    iness
    0.17
     thing
    0.17
    Activations Density 0.683%

    No Known Activations