© 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. 72254
    Prev
    Next
    INDEX
    Explanations

    useState

    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
    <LM
    -0.07
     recherche
    -0.07
    	UP
    -0.06
     temp
    -0.06
    ᨾ
    -0.06
     TForm
    -0.06
    某一
    -0.06
    _INCREF
    -0.06
    dfs
    -0.06
    就越
    -0.06
    POSITIVE LOGITS
     hacker
    0.07
    好好
    0.07
     Conscious
    0.07
     opioid
    0.06
    势力
    0.06
     endoth
    0.06
    سعيد
    0.06
    限量
    0.06
    院
    0.06
     morality
    0.06
    Activations Density 0.002%

    No Known Activations