© 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. 28529
    Prev
    Next
    INDEX
    Explanations

    lose stability, validity, moisture

    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
    AZE
    -0.10
    PD
    -0.09
    pd
    -0.09
    ENTE
    -0.08
    RAL
    -0.08
     treasure
    -0.08
    BK
    -0.08
    Replacement
    -0.08
    oba
    -0.08
    alia
    -0.08
    POSITIVE LOGITS
     strength
    0.18
     ability
    0.17
     abilities
    0.15
     characteristics
    0.15
     properties
    0.15
     potency
    0.15
     responsiveness
    0.15
     qualities
    0.14
     capability
    0.14
     its
    0.14
    Activations Density 0.191%

    No Known Activations