© 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. 31349
    Prev
    Next
    INDEX
    Explanations

    study in or of

    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
    park
    -0.11
    sch
    -0.10
    sen
    -0.10
    speed
    -0.10
    ized
    -0.10
    sel
    -0.10
    sim
    -0.10
    nos
    -0.09
    -leaning
    -0.09
    urator
    -0.09
    POSITIVE LOGITS
     abroad
    0.14
    blr
    0.14
    ying
    0.13
    ied
    0.13
    rama
    0.12
     habits
    0.12
    /work
    0.11
    bay
    0.10
     perms
    0.10
    /reference
    0.10
    Activations Density 0.160%

    No Known Activations