© 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. 31930
    Prev
    Next
    INDEX
    Explanations

    unknown or unfamiliar concepts

    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
     loosely
    -0.11
    anche
    -0.10
    ncy
    -0.10
    alie
    -0.10
    urger
    -0.10
     App
    -0.09
    atte
    -0.09
    zie
    -0.09
    anh
    -0.09
     Loose
    -0.09
    POSITIVE LOGITS
     unfamiliar
    0.40
     unknown
    0.34
     unseen
    0.30
     unheard
    0.25
    unknown
    0.25
     whom
    0.24
     Unknown
    0.24
     unrecognized
    0.23
    Unknown
    0.21
     unfore
    0.21
    Activations Density 0.515%

    No Known Activations