© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    them or it

    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
    Its
    -0.19
     Its
    -0.17
     thereof
    -0.15
     its
    -0.15
     therein
    -0.15
    —it
    -0.13
    its
    -0.13
    âĢ¦it
    -0.13
    ,it
    -0.13
    .It
    -0.12
    POSITIVE LOGITS
     them
    0.13
     him
    0.10
    them
    0.09
    Them
    0.08
     Them
    0.08
    bah
    0.07
    rai
    0.07
    iar
    0.07
    zy
    0.06
    Mos
    0.06
    Activations Density 0.160%

    No Known Activations