© 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. 28974
    Prev
    Next
    INDEX
    Explanations

    terms of endearment/address

    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
     goodness
    -0.09
    kal
    -0.09
    unicorn
    -0.08
    ?a
    -0.08
    furt
    -0.08
     OMG
    -0.08
    oble
    -0.08
    .Please
    -0.08
    acco
    -0.08
     Stout
    -0.08
    POSITIVE LOGITS
     bingo
    0.12
     ;)
    0.11
    onta
    0.11
     tard
    0.10
     ~=
    0.10
     ðŁĺī
    0.10
     lumber
    0.10
     ante
    0.10
     wanna
    0.10
     dipped
    0.10
    Activations Density 0.018%

    No Known Activations