© 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. 115938
    Prev
    Next
    INDEX
    Explanations

    that's why

    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
    DS
    -0.09
     include
    -0.08
    ios
    -0.08
     suffice
    -0.08
     there
    -0.07
    it
    -0.07
     Moy
    -0.07
    apon
    -0.07
     Were
    -0.06
    isch
    -0.06
    POSITIVE LOGITS
    aru
    0.13
    éĥ
    0.12
    chl
    0.12
    olie
    0.12
    eto
    0.12
    ROL
    0.11
    .sup
    0.11
    antas
    0.11
     balk
    0.11
    canf
    0.11
    Activations Density 0.008%

    No Known Activations