© 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. 113265
    Prev
    Next
    INDEX
    Explanations

    ab + suffix

    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
    orum
    -0.09
    thinkable
    -0.08
    IED
    -0.08
     Burke
    -0.08
     snapshot
    -0.08
    walk
    -0.08
    ings
    -0.08
     mockery
    -0.08
    oppable
    -0.08
    ied
    -0.08
    POSITIVE LOGITS
    ridged
    0.13
    ovement
    0.13
    normally
    0.13
    propri
    0.11
    fg
    0.11
    aaaaaaaa
    0.10
    duct
    0.10
     swell
    0.10
    FG
    0.10
    nnen
    0.10
    Activations Density 0.007%

    No Known Activations