© 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. 19-RESID-POST-AA
    11. 4039
    Prev
    Next
    INDEX
    Explanations

    code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    休闲
    -0.07
     Short
    -0.07
    雇主
    -0.07
     dispersion
    -0.07
    IME
    -0.07
    وبر
    -0.07
    队伍建设
    -0.07
    Bien
    -0.07
    交给
    -0.06
    が多い
    -0.06
    POSITIVE LOGITS
     האחרון
    0.07
    赞助
    0.07
    倓
    0.06
     mastered
    0.06
    ermalink
    0.06
     Katherine
    0.06
    (previous
    0.06
    upuncture
    0.06
    								
↵
    0.06
     Fukushima
    0.06
    Activations Density 0.028%

    No Known Activations