© 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. 113855
    Prev
    Next
    INDEX
    Explanations

    archives and tags

    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
    cis
    -0.09
     absolutely
    -0.08
    çĤ¹åĩ»
    -0.08
     heavily
    -0.08
     above
    -0.08
     um
    -0.08
     touches
    -0.08
     tonight
    -0.07
    NL
    -0.07
     compos
    -0.07
    POSITIVE LOGITS
     Archives
    0.17
     archives
    0.16
     tagged
    0.16
     archive
    0.15
     tag
    0.13
    illet
    0.13
    “↵↵
    0.13
    /tags
    0.12
     Tag
    0.12
    Archive
    0.12
    Activations Density 0.099%

    No Known Activations