© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ﴿
    -0.07
    IEnumerator
    -0.07
    コー
    -0.07
    诠释
    -0.07
    @dynamic
    -0.07
     deck
    -0.07
    ăr
    -0.07
     она
    -0.07
    ợi
    -0.07
    🎇
    -0.07
    POSITIVE LOGITS
     Ally
    0.07
     UINT
    0.07
    Have
    0.07
    郸
    0.06
    ド
    0.06
     gotta
    0.06
     FR
    0.06
    ociety
    0.06
     ()↵↵
    0.06
     NATIONAL
    0.06
    Activations Density 0.002%

    No Known Activations