© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91616
    Prev
    Next
    INDEX
    Explanations

    ogen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("-");↵
    -0.08
     advocated
    -0.07
     обеспеч
    -0.07
     spur
    -0.07
    돗
    -0.07
    溅
    -0.07
    犨
    -0.07
    프로그램
    -0.07
     Populate
    -0.07
     burn
    -0.07
    POSITIVE LOGITS
    meet
    0.07
     ATTACK
    0.07
    MEM
    0.07
    	const
    0.07
     coleg
    0.06
    定制
    0.06
     Steele
    0.06
    Lie
    0.06
    (CON
    0.06
     democr
    0.06
    Activations Density 0.001%

    No Known Activations