© 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. 90636
    Prev
    Next
    INDEX
    Explanations

    Ma'alul, Maohi, Ma Xiaotiao, Ma Can, Maier, Maangchi

    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
     neg
    -0.11
     un
    -0.09
     distinct
    -0.09
    è¾¾
    -0.08
     redo
    -0.08
     ground
    -0.08
     ï
    -0.08
     recourse
    -0.08
     assaults
    -0.08
     pro
    -0.08
    POSITIVE LOGITS
    yh
    0.12
     Misc
    0.11
    enance
    0.10
    JOR
    0.10
    esto
    0.10
    ersonic
    0.10
    orget
    0.10
    upy
    0.10
    lico
    0.10
    eline
    0.09
    Activations Density 0.087%

    No Known Activations