© 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. 49829
    Prev
    Next
    INDEX
    Explanations

    as if to add

    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
    rio
    -0.11
     indiscrim
    -0.11
     helf
    -0.11
    omed
    -0.10
     Crack
    -0.10
    idon
    -0.10
    aris
    -0.10
    izont
    -0.10
     Schl
    -0.10
    afil
    -0.10
    POSITIVE LOGITS
     icing
    0.24
     additionally
    0.22
     furthermore
    0.20
     added
    0.19
     further
    0.19
     insult
    0.18
     adds
    0.18
     compound
    0.17
     add
    0.17
     complic
    0.17
    Activations Density 0.064%

    No Known Activations