© 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. 92196
    Prev
    Next
    INDEX
    Explanations

    injecting or injection

    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
     oppos
    -0.09
     ged
    -0.09
     clas
    -0.09
    аÑĤа
    -0.08
    anst
    -0.08
     nib
    -0.08
    iona
    -0.08
     fam
    -0.08
     Inform
    -0.08
     wrapping
    -0.07
    POSITIVE LOGITS
    .Inject
    0.20
     injecting
    0.17
     injection
    0.15
     injections
    0.15
     Injection
    0.14
    inject
    0.14
     Inject
    0.14
     injected
    0.14
     INTO
    0.13
    Injection
    0.13
    Activations Density 0.167%

    No Known Activations