© 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. 30008
    Prev
    Next
    INDEX
    Explanations

    is like this:

    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
     Hodg
    -0.10
    abox
    -0.10
     voc
    -0.09
    .Meta
    -0.09
    /link
    -0.09
     Ro
    -0.09
    ims
    -0.08
    iners
    -0.08
     terminator
    -0.08
     Sanct
    -0.08
    POSITIVE LOGITS
    以ä¸ĭ
    0.26
     following
    0.25
     seguint
    0.23
    :
    0.22
     Ñģлед
    0.19
    following
    0.18
     follows
    0.18
     simple
    0.17
     suiv
    0.17
     Following
    0.17
    Activations Density 1.605%

    No Known Activations