© 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. 6455
    Prev
    Next
    INDEX
    Explanations

    it is clear/easy/important

    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
    lyn
    -0.09
     isn
    -0.08
     styl
    -0.07
    matter
    -0.07
     resembling
    -0.07
     basal
    -0.06
     Protected
    -0.06
     is
    -0.06
     belonging
    -0.06
    elyn
    -0.06
    POSITIVE LOGITS
     possible
    0.17
     apparent
    0.15
     clear
    0.15
     evident
    0.14
    possible
    0.14
     Possible
    0.14
     implied
    0.13
     obvious
    0.13
     POSS
    0.13
     easier
    0.13
    Activations Density 0.120%

    No Known Activations