© 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. 29858
    Prev
    Next
    INDEX
    Explanations

    analys

    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
    kap
    -0.09
    arna
    -0.08
    ingly
    -0.08
     Nude
    -0.08
    aire
    -0.08
    ADR
    -0.08
    ARI
    -0.07
     sequ
    -0.07
    aec
    -0.07
     narr
    -0.07
    POSITIVE LOGITS
    ges
    0.16
    yses
    0.16
    isis
    0.15
     anal
    0.15
    ysi
    0.14
    YSIS
    0.14
    ogue
    0.14
    ysize
    0.13
     Anal
    0.13
    isa
    0.13
    Activations Density 0.016%

    No Known Activations