© 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. 48349
    Prev
    Next
    INDEX
    Explanations

    instead

    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
    êt
    -0.11
    —not
    -0.11
    ixon
    -0.10
    eus
    -0.10
    ):-
    -0.10
     WITHOUT
    -0.10
    zure
    -0.10
     Aub
    -0.10
     pena
    -0.10
    auc
    -0.10
    POSITIVE LOGITS
     instead
    0.44
    instead
    0.35
     Instead
    0.34
    Instead
    0.33
     alternatively
    0.17
     resort
    0.14
     opt
    0.13
     alternatives
    0.12
     alternative
    0.11
     plutôt
    0.11
    Activations Density 0.207%

    No Known Activations