© 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. 47603
    Prev
    Next
    INDEX
    Explanations

    penetration and invasion

    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
     constr
    -0.10
     transfers
    -0.10
     transfer
    -0.09
    transfer
    -0.09
     rotate
    -0.09
    ewan
    -0.09
     transf
    -0.09
    gis
    -0.09
    ANI
    -0.09
     Transfer
    -0.08
    POSITIVE LOGITS
     probing
    0.23
     penetration
    0.22
     probes
    0.21
     penetrating
    0.20
     probe
    0.20
     deeper
    0.19
     intrusive
    0.19
     exploration
    0.18
     invasive
    0.18
     intrusion
    0.18
    Activations Density 0.012%

    No Known Activations