© 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. 112430
    Prev
    Next
    INDEX
    Explanations

    rod, knob, or slider components

    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
    anean
    -0.10
    ãĤ£
    -0.10
    abox
    -0.10
    æį
    -0.09
    agara
    -0.09
    plode
    -0.09
    uhan
    -0.09
    uml
    -0.09
    ABCDE
    -0.09
    /exp
    -0.09
    POSITIVE LOGITS
    ship
    0.13
    ial
    0.13
    ular
    0.12
    ski
    0.12
    elling
    0.10
    rd
    0.10
    /slider
    0.10
    manship
    0.10
    iale
    0.09
    ter
    0.09
    Activations Density 0.003%

    No Known Activations