© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 60015
    Prev
    Next
    INDEX
    Explanations

    computer commands

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    营业执照
    -0.07
    ɶ
    -0.06
    UserController
    -0.06
     joven
    -0.06
     agricult
    -0.06
    🍨
    -0.06
    讨厌
    -0.06
     childbirth
    -0.06
     Independent
    -0.06
     NSDictionary
    -0.06
    POSITIVE LOGITS
    _BAR
    0.08
    IMS
    0.08
    下班
    0.08
    unds
    0.07
     Zar
    0.07
    朱
    0.07
    湎
    0.07
    خط
    0.07
     wording
    0.07
    Posts
    0.07
    Activations Density 0.016%

    No Known Activations