© 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. 50470
    Prev
    Next
    INDEX
    Explanations

    or issued, could, reference, near, will, before, are, renamed, installed

    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
    ixa
    -0.09
    rip
    -0.08
    azz
    -0.08
    ky
    -0.08
     weakest
    -0.08
    ittest
    -0.08
     Gef
    -0.07
     Stored
    -0.07
    IPH
    -0.07
    ori
    -0.07
    POSITIVE LOGITS
     quasi
    0.21
     closely
    0.20
     close
    0.19
     pseudo
    0.18
     equivalent
    0.17
     CLOSE
    0.17
     Close
    0.17
    -close
    0.17
     near
    0.16
    -like
    0.16
    Activations Density 0.573%

    No Known Activations