© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115588
    Prev
    Next
    INDEX
    Explanations

    armstrong, armagh, armament, armchair

    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
     Poor
    -0.09
     poor
    -0.08
     Shaw
    -0.08
    Poor
    -0.07
    verter
    -0.07
     cloudy
    -0.07
    moz
    -0.07
    inel
    -0.07
    efault
    -0.07
    cales
    -0.07
    POSITIVE LOGITS
    ored
    0.15
    chair
    0.15
    aments
    0.15
    aret
    0.14
    oured
    0.14
    ament
    0.14
    atures
    0.13
    endar
    0.13
    strong
    0.12
    ature
    0.12
    Activations Density 0.020%

    No Known Activations