© 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. 26536
    Prev
    Next
    INDEX
    Explanations

    Ley names and prefixes

    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
     hor
    -0.09
    Refer
    -0.08
     conditional
    -0.08
    rey
    -0.08
    aga
    -0.08
     Gri
    -0.08
     aggrav
    -0.07
     morph
    -0.07
    alsa
    -0.07
    hor
    -0.07
    POSITIVE LOGITS
    ders
    0.12
    bron
    0.11
    dig
    0.11
    utenant
    0.11
    aders
    0.11
    likelihood
    0.10
     Pik
    0.10
    -det
    0.10
    opard
    0.10
     Lad
    0.10
    Activations Density 0.070%

    No Known Activations