© 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. 7886
    Prev
    Next
    INDEX
    Explanations

    song titles and phrases

    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
     Garner
    -0.07
    /${
    -0.07
    rett
    -0.07
    ...\
    -0.07
    ersh
    -0.06
    EOF
    -0.06
    usty
    -0.06
    _hint
    -0.06
     ...
    -0.06
    ..."↵↵
    -0.06
    POSITIVE LOGITS
    #aa
    0.13
    (ed
    0.12
     ê
    0.11
    /live
    0.11
     pratic
    0.11
     newcom
    0.11
     sucess
    0.11
    ,eg
    0.10
    (er
    0.10
     suce
    0.10
    Activations Density 3.019%

    No Known Activations