© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 16909
    Prev
    Next
    INDEX
    Explanations

    problem or solution clarification

    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
    ï¼Įå¹¶
    -0.14
    ,and
    -0.13
    â̦and
    -0.12
     &,
    -0.12
    ãĢģ↵↵
    -0.11
    ?,
    -0.10
    ï¼Īç¬ij
    -0.10
     ,[
    -0.10
    ãĢģ
    -0.10
    ,eg
    -0.10
    POSITIVE LOGITS
    :
    0.24
    —they
    0.17
     –
    0.15
    —you
    0.13
    —he
    0.13
    —we
    0.13
    ï¼ļ
    0.12
    —the
    0.12
     -
    0.12
    —it
    0.12
    Activations Density 0.247%

    No Known Activations