© 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. 4601
    Prev
    Next
    INDEX
    Explanations

    amber, ember, resin

    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
     poi
    -0.12
    ifo
    -0.10
    Accordion
    -0.10
    IFO
    -0.10
    roi
    -0.10
     clown
    -0.10
    shiv
    -0.10
     Matth
    -0.09
     gesture
    -0.09
    OX
    -0.09
    POSITIVE LOGITS
     Amber
    0.34
     amber
    0.34
    amber
    0.26
     Ember
    0.18
    é»
    0.16
     ember
    0.16
     AMA
    0.14
     resin
    0.14
     AMS
    0.13
     yellow
    0.12
    Activations Density 0.056%

    No Known Activations