© 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. 117106
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bian
    -0.13
    sing
    -0.13
    ovan
    -0.11
    nya
    -0.11
    nh
    -0.11
    gens
    -0.11
    reb
    -0.10
    si
    -0.10
     UNICODE
    -0.10
    aub
    -0.10
    POSITIVE LOGITS
     unm
    0.09
    ÑģÑĤÑĮ
    0.09
    ikh
    0.09
    quer
    0.09
    icago
    0.08
    APT
    0.08
    apt
    0.08
     Clifford
    0.08
    ivo
    0.08
     CAP
    0.08
    Activations Density 0.000%

    No Known Activations