© 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. 112237
    Prev
    Next
    INDEX
    Explanations

    if and only if

    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
    ?action
    -0.12
    dal
    -0.11
    _mB
    -0.11
    bach
    -0.11
    odash
    -0.11
    leck
    -0.11
    ва
    -0.11
    _tD
    -0.11
    -fr
    -0.11
    {Name
    -0.11
    POSITIVE LOGITS
     and
    0.48
    —and
    0.46
    –and
    0.40
    (and
    0.37
    and
    0.33
    -and
    0.32
    	and
    0.31
    ,and
    0.29
    —or
    0.25
    _and
    0.24
    Activations Density 1.587%

    No Known Activations