© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8781
    Prev
    Next
    INDEX
    Explanations

    charging network protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carrier
    -0.10
    iyas
    -0.10
     Carrier
    -0.10
     carrier
    -0.10
     carriage
    -0.10
    jem
    -0.09
    ç±
    -0.09
     dist
    -0.09
    carrier
    -0.08
     Engines
    -0.08
    POSITIVE LOGITS
     charging
    0.29
    charging
    0.23
     EV
    0.23
     Charging
    0.23
     Charge
    0.20
     charge
    0.19
    EV
    0.19
     charg
    0.19
     charger
    0.19
    åħħ
    0.19
    Activations Density 0.025%

    No Known Activations