© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15-RESID-POST-AA
    11. 5470
    Prev
    Next
    INDEX
    Explanations

    safety standards

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    	assertEquals
    -0.08
    >",
    -0.07
    句子
    -0.07
    꿉
    -0.07
     „
    -0.07
    绝对不会
    -0.07
    „
    -0.07
    "},
    -0.07
     vox
    -0.06
     null
    -0.06
    POSITIVE LOGITS
     massac
    0.07
    emain
    0.07
    organ
    0.07
     analytic
    0.07
     rect
    0.07
     travels
    0.07
    Records
    0.07
     hồng
    0.07
    ohana
    0.07
    printw
    0.07
    Activations Density 0.003%

    No Known Activations