© 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. 26172
    Prev
    Next
    INDEX
    Explanations

    leaning toward or favoring

    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
     unfit
    -0.10
     indirectly
    -0.10
     conflic
    -0.09
    unk
    -0.09
    uncture
    -0.08
    uka
    -0.08
    bounding
    -0.08
    inking
    -0.08
    pin
    -0.08
     Champ
    -0.08
    POSITIVE LOGITS
     towards
    0.36
     toward
    0.34
     Tow
    0.31
     Towards
    0.29
    Towards
    0.28
    åIJij
    0.23
     leans
    0.23
     favor
    0.20
    owards
    0.20
     lean
    0.20
    Activations Density 0.158%

    No Known Activations