© 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. 115911
    Prev
    Next
    INDEX
    Explanations

    nin, ninv, nine, ni, ninte

    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
    sville
    -0.11
    -paid
    -0.10
    DEM
    -0.10
    sst
    -0.10
    aug
    -0.09
     wilt
    -0.09
    象
    -0.09
    side
    -0.09
    alist
    -0.09
    494
    -0.09
    POSITIVE LOGITS
    eties
    0.13
    ete
    0.12
    hydr
    0.11
    azu
    0.11
    jal
    0.10
    etailed
    0.09
    quirer
    0.09
    jax
    0.08
    ety
    0.08
    jas
    0.08
    Activations Density 0.030%

    No Known Activations