© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16345
    Prev
    Next
    INDEX
    Explanations

    h followed by 'grow', 'umped', 'RP'

    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
    eps
    -0.13
    idor
    -0.13
    eu
    -0.12
    ech
    -0.12
    ettel
    -0.12
    eid
    -0.12
    e
    -0.12
    eed
    -0.11
    -Semit
    -0.11
    ested
    -0.11
    POSITIVE LOGITS
     incre
    0.10
    hh
    0.09
    istry
    0.08
    nr
    0.08
    ery
    0.08
    dm
    0.08
    mong
    0.08
    entication
    0.08
    wise
    0.07
    hhh
    0.07
    Activations Density 0.001%

    No Known Activations