© 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. 49595
    Prev
    Next
    INDEX
    Explanations

    As- prefix

    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
     prere
    -0.09
     instability
    -0.09
     Feast
    -0.09
    apis
    -0.09
    hoc
    -0.09
     scales
    -0.08
     pearl
    -0.08
    лен
    -0.08
     Haram
    -0.08
     accord
    -0.08
    POSITIVE LOGITS
     AS
    0.19
    /as
    0.17
     As
    0.17
    _As
    0.15
    _AS
    0.15
    .as
    0.14
    asy
    0.14
     ASF
    0.14
    ASY
    0.14
    AS
    0.13
    Activations Density 0.256%

    No Known Activations