© 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. 116673
    Prev
    Next
    INDEX
    Explanations

    i have a question

    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
    /oct
    -0.12
     gratuit
    -0.11
     Felipe
    -0.11
    zer
    -0.11
    :error
    -0.11
     citation
    -0.11
     Citation
    -0.10
    hint
    -0.10
    iever
    -0.10
     curb
    -0.10
    POSITIVE LOGITS
     confess
    0.08
     disclose
    0.08
     wanna
    0.08
     confession
    0.07
    .conf
    0.07
     show
    0.07
    enda
    0.07
     tore
    0.07
    Show
    0.07
    -conf
    0.07
    Activations Density 0.063%

    No Known Activations