© 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. 92173
    Prev
    Next
    INDEX
    Explanations

    sharing information or oneself

    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
    efa
    -0.09
    ision
    -0.09
    iy
    -0.09
    eva
    -0.09
    eb
    -0.08
    nya
    -0.08
    efs
    -0.08
    acro
    -0.08
     hull
    -0.08
    ny
    -0.08
    POSITIVE LOGITS
     oneself
    0.60
     yourself
    0.38
     your
    0.28
     yourselves
    0.26
    your
    0.25
     Yourself
    0.25
     ourselves
    0.21
     Ones
    0.19
     ones
    0.18
     Your
    0.18
    Activations Density 0.747%

    No Known Activations