© 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. 31197
    Prev
    Next
    INDEX
    Explanations

    of

    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
    olean
    -0.09
    ocale
    -0.08
     TAR
    -0.08
     Dud
    -0.08
    onte
    -0.08
    ubern
    -0.08
     Butler
    -0.08
     perms
    -0.08
    ertime
    -0.08
    âĨIJ
    -0.07
    POSITIVE LOGITS
     of
    0.42
    _of
    0.30
    of
    0.29
     cá»§a
    0.29
     Of
    0.28
    	of
    0.28
    .of
    0.27
     OF
    0.26
    Of
    0.25
    -of
    0.25
    Activations Density 0.917%

    No Known Activations