© 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. 115462
    Prev
    Next
    INDEX
    Explanations

    scent and fragrance

    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
    abouts
    -0.11
    ishly
    -0.11
    iggins
    -0.10
     physic
    -0.09
    s
    -0.09
    ieurs
    -0.09
    onet
    -0.09
    hoe
    -0.08
    mina
    -0.08
    h
    -0.08
    POSITIVE LOGITS
    less
    0.14
    ual
    0.13
    ing
    0.12
    emente
    0.12
    rix
    0.12
    ral
    0.11
    /avatar
    0.11
    ÑĥÑī
    0.11
    prov
    0.11
    eya
    0.11
    Activations Density 0.002%

    No Known Activations