© 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. 7-RESID-POST-AA
    11. 12330
    Prev
    Next
    INDEX
    Explanations

    software licenses/code

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     excerpts
    -0.08
    湉
    -0.07
     orbs
    -0.07
     transcript
    -0.07
    딘
    -0.07
     roles
    -0.07
    网球
    -0.07
     Trên
    -0.07
    <n
    -0.06
     ministries
    -0.06
    POSITIVE LOGITS
    かり
    0.07
    	NULL
    0.07
     احد
    0.07
    abhäng
    0.07
    _UN
    0.07
    owied
    0.07
    عائلة
    0.07
    �
    0.07
    垃圾分类
    0.07
     horizontally
    0.07
    Activations Density 0.004%

    No Known Activations