© 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. 30939
    Prev
    Next
    INDEX
    Explanations

    same followed by specific word

    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
    same
    -0.11
    åIJĮ
    -0.10
     same
    -0.10
    ted
    -0.10
     Same
    -0.10
     similar
    -0.09
    agem
    -0.09
    Same
    -0.09
    /ag
    -0.09
    amble
    -0.09
    POSITIVE LOGITS
    -sex
    0.25
    /op
    0.17
     thing
    0.17
     exact
    0.16
    -origin
    0.16
    -old
    0.15
     amount
    0.14
     old
    0.13
    -day
    0.13
     kind
    0.13
    Activations Density 0.209%

    No Known Activations