© 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. 29980
    Prev
    Next
    INDEX
    Explanations

    is served, is home, is situated

    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
     Lives
    -0.12
     lasts
    -0.11
    dee
    -0.10
     lives
    -0.10
    OTA
    -0.10
     collaps
    -0.10
     triggered
    -0.10
    izio
    -0.10
    rust
    -0.10
     lasted
    -0.10
    POSITIVE LOGITS
     boasts
    0.20
     host
    0.19
     hosts
    0.18
     home
    0.17
     renowned
    0.17
     boasted
    0.16
     boasting
    0.16
     hosting
    0.16
     boast
    0.15
     rich
    0.14
    Activations Density 0.242%

    No Known Activations