© 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. 112205
    Prev
    Next
    INDEX
    Explanations

    object of desire

    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
    pty
    -0.10
    åĪ«
    -0.09
    ubs
    -0.09
     belongings
    -0.08
    -headed
    -0.08
    alo
    -0.08
     universe
    -0.08
    ãĥĥ
    -0.08
    avy
    -0.08
    kit
    -0.08
    POSITIVE LOGITS
     aff
    0.12
    athe
    0.11
    erde
    0.11
    aco
    0.11
     Agr
    0.10
    (Source
    0.10
    acha
    0.10
     salv
    0.10
    mez
    0.10
    templ
    0.10
    Activations Density 0.002%

    No Known Activations