© 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. 17271
    Prev
    Next
    INDEX
    Explanations

    words ending in ful

    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
    ed
    -0.14
    est
    -0.13
    ef
    -0.13
    imal
    -0.11
    ìłģ
    -0.11
    ish
    -0.11
    ification
    -0.11
    ical
    -0.10
    able
    -0.10
    icle
    -0.10
    POSITIVE LOGITS
    lest
    0.37
    s
    0.22
    ness
    0.17
    NESS
    0.17
    nes
    0.16
    mente
    0.14
    -looking
    0.13
    sie
    0.11
    y
    0.11
     ness
    0.11
    Activations Density 0.088%

    No Known Activations