© 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. 49666
    Prev
    Next
    INDEX
    Explanations

    endings like 'an', 'wan', 'ran'

    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
    gar
    -0.14
    gun
    -0.14
    down
    -0.14
    gang
    -0.14
    gart
    -0.14
    ness
    -0.13
    girl
    -0.13
    skin
    -0.13
    gen
    -0.13
    sk
    -0.13
    POSITIVE LOGITS
    lı
    0.17
    omaly
    0.16
    ne
    0.16
    alysis
    0.16
    egra
    0.15
    throp
    0.15
    etwork
    0.14
    ese
    0.14
    ifest
    0.14
    ufacturer
    0.14
    Activations Density 0.709%

    No Known Activations