© 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. 90968
    Prev
    Next
    INDEX
    Explanations

    applicability to audience

    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
     dim
    -0.09
    509
    -0.09
     alias
    -0.09
    yk
    -0.09
    519
    -0.08
    ahn
    -0.08
    Doing
    -0.08
     raft
    -0.08
    Idle
    -0.08
    INST
    -0.08
    POSITIVE LOGITS
     suitability
    0.26
     suitable
    0.25
     Suitable
    0.23
     cater
    0.20
    suit
    0.20
    Suit
    0.20
     universal
    0.19
     suited
    0.19
     applic
    0.18
     appeal
    0.18
    Activations Density 0.627%

    No Known Activations