© 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. 30640
    Prev
    Next
    INDEX
    Explanations

    Val names

    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
     val
    -0.10
     valued
    -0.09
    _val
    -0.09
     Val
    -0.08
     valve
    -0.08
     Valor
    -0.08
     valuable
    -0.08
     Valve
    -0.08
     Appropri
    -0.08
    heel
    -0.08
    POSITIVE LOGITS
    core
    0.11
    lec
    0.11
    ocs
    0.11
    car
    0.11
    spa
    0.11
    entic
    0.11
    agged
    0.11
    dq
    0.10
    ois
    0.10
    Ny
    0.10
    Activations Density 0.006%

    No Known Activations