© 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. 7889
    Prev
    Next
    INDEX
    Explanations

    words starting with rel

    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
    jer
    -0.09
     ê±
    -0.09
    ÑģÑĤÑĢ
    -0.08
    cheng
    -0.08
    omat
    -0.08
     Jer
    -0.08
    icles
    -0.08
    odes
    -0.08
    achment
    -0.08
     Eh
    -0.08
    POSITIVE LOGITS
     relay
    0.13
     rel
    0.11
    ment
    0.11
    ength
    0.10
    lict
    0.10
    atively
    0.10
    ishing
    0.10
    tz
    0.10
    rac
    0.10
     inward
    0.09
    Activations Density 0.005%

    No Known Activations