© 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. 3916
    Prev
    Next
    INDEX
    Explanations

    on surfaces

    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
    noon
    -0.10
     Tomb
    -0.10
    lov
    -0.10
     tether
    -0.10
     confess
    -0.09
     summer
    -0.09
     Ton
    -0.09
     controls
    -0.09
     patiently
    -0.09
    jb
    -0.09
    POSITIVE LOGITS
     ti
    0.14
     toes
    0.11
     vert
    0.11
     oci
    0.09
    icht
    0.09
     Atkins
    0.09
     Replay
    0.09
     Powell
    0.08
     pedals
    0.08
    askan
    0.08
    Activations Density 0.034%

    No Known Activations