© 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. 25858
    Prev
    Next
    INDEX
    Explanations

    names and items

    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
    peror
    -0.09
    reste
    -0.09
     rest
    -0.09
    nish
    -0.08
    ARING
    -0.08
    bern
    -0.08
    anka
    -0.08
     Fuji
    -0.08
    Primitive
    -0.08
    cona
    -0.08
    POSITIVE LOGITS
    ys
    0.12
    YS
    0.10
    urd
    0.09
     hum
    0.09
    (s
    0.09
     Hum
    0.08
    (er
    0.08
     PK
    0.08
    _es
    0.08
    ibs
    0.08
    Activations Density 0.699%

    No Known Activations