© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6071
    Prev
    Next
    INDEX
    Explanations

    medical and negative prefixes/suffixes yielding specific words

    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
    ologically
    -0.11
    appy
    -0.11
    ulative
    -0.10
    olated
    -0.10
     concentrated
    -0.10
    ILLED
    -0.10
    chy
    -0.09
    ationally
    -0.09
    icated
    -0.09
     favourable
    -0.09
    POSITIVE LOGITS
    ignment
    0.11
    quisition
    0.11
    ioxide
    0.10
    ization
    0.10
    ities
    0.10
    clerosis
    0.09
    atement
    0.09
    ference
    0.09
    moil
    0.09
    ulance
    0.09
    Activations Density 1.416%

    No Known Activations