© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    familiarity from context

    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
     bul
    -0.10
     invite
    -0.10
    abe
    -0.10
    Invite
    -0.09
     inviting
    -0.09
     Tat
    -0.09
     strongly
    -0.09
    fld
    -0.09
     Tk
    -0.09
     Invite
    -0.09
    POSITIVE LOGITS
    _te
    0.11
     familiar
    0.11
     Fam
    0.10
    .Te
    0.10
     Tablet
    0.10
    /Table
    0.09
     familiarity
    0.09
     Symbol
    0.09
     showers
    0.09
    romo
    0.09
    Activations Density 0.007%

    No Known Activations