© 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. 112699
    Prev
    Next
    INDEX
    Explanations

    acquaintance or familiarity

    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
    483
    -0.09
    ola
    -0.09
    laden
    -0.09
     Junction
    -0.08
     duplex
    -0.08
    imit
    -0.08
    lok
    -0.08
    IMIT
    -0.08
    CU
    -0.08
    HF
    -0.08
    POSITIVE LOGITS
     acquaintance
    0.38
     acquainted
    0.37
     acquaint
    0.33
     familiarity
    0.29
     familiar
    0.26
     Fam
    0.24
     met
    0.23
     knew
    0.22
     known
    0.21
     knowing
    0.21
    Activations Density 0.168%

    No Known Activations