© 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. 49211
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or articles after actions

    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
     deren
    -0.12
    azar
    -0.11
     Lazar
    -0.10
    uits
    -0.10
    ÑĭÑħ
    -0.10
    odem
    -0.10
     Whit
    -0.10
    ICC
    -0.10
    _Al
    -0.10
    -inv
    -0.10
    POSITIVE LOGITS
     your
    0.19
    your
    0.15
     device
    0.14
     Your
    0.14
     ваÑĪ
    0.14
    Your
    0.14
     votre
    0.12
    >Your
    0.11
     unit
    0.10
     devices
    0.10
    Activations Density 0.824%

    No Known Activations