© 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. 48347
    Prev
    Next
    INDEX
    Explanations

    Unity, gaming, or technical code structure

    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
     Suzuki
    -0.13
     Wendy
    -0.13
     Lama
    -0.11
     Tcl
    -0.11
     Perl
    -0.10
    (#
    -0.10
     Muj
    -0.10
     Hulu
    -0.10
     Rud
    -0.10
     Chattanooga
    -0.10
    POSITIVE LOGITS
     Shepard
    0.31
     Garr
    0.22
     DLC
    0.19
     Reaper
    0.17
     Mass
    0.17
     Citadel
    0.13
     Ryder
    0.13
     Shepherd
    0.13
     Mercer
    0.13
     Miranda
    0.12
    Activations Density 0.216%

    No Known Activations