© 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. 33150
    Prev
    Next
    INDEX
    Explanations

    echo, echoes, resonate

    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
     Inhal
    -0.12
     leash
    -0.11
     spoiled
    -0.10
    EXPORT
    -0.10
     segreg
    -0.10
    -eye
    -0.10
    ,eg
    -0.10
     Phill
    -0.10
     MASK
    -0.09
     Benson
    -0.09
    POSITIVE LOGITS
     echo
    0.15
     echoes
    0.15
     chambers
    0.15
     Echo
    0.14
     resonate
    0.14
     ech
    0.14
     reson
    0.13
     rever
    0.13
    Echo
    0.12
     echoing
    0.12
    Activations Density 0.026%

    No Known Activations