© 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. 15272
    Prev
    Next
    INDEX
    Explanations

    likely to follow L

    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
    ink
    -0.12
    ines
    -0.11
    ayer
    -0.11
    iv
    -0.11
    esson
    -0.11
    ast
    -0.10
    arge
    -0.10
    ayers
    -0.10
    abel
    -0.10
    ou
    -0.10
    POSITIVE LOGITS
    educ
    0.14
    uria
    0.14
    ively
    0.14
    ichten
    0.13
    lan
    0.13
    ecom
    0.13
    lane
    0.13
    ledo
    0.13
    epad
    0.12
    opes
    0.12
    Activations Density 0.236%

    No Known Activations