© 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. 28964
    Prev
    Next
    INDEX
    Explanations

    aunt or sister

    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
    habit
    -0.11
    aeda
    -0.10
    hed
    -0.09
    ateg
    -0.09
    pi
    -0.09
     Crom
    -0.09
    vez
    -0.09
     POLITICO
    -0.08
     quaint
    -0.08
    hung
    -0.08
    POSITIVE LOGITS
    ie
    0.28
    ies
    0.21
    IE
    0.16
    tie
    0.12
    iest
    0.12
    iem
    0.11
    ness
    0.11
    IES
    0.11
    zilla
    0.11
    (er
    0.11
    Activations Density 0.002%

    No Known Activations