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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23-RESID-POST-AA
    11. 129994
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alb
    -0.07
     negativity
    -0.07
    ilogy
    -0.07
    ajs
    -0.07
    igt
    -0.06
    аст
    -0.06
    idge
    -0.06
    暫
    -0.06
    valuator
    -0.06
     Bakanlığı
    -0.06
    POSITIVE LOGITS
    Token
    0.07
    体现
    0.07
    勤奋
    0.07
    特征
    0.07
    .Tab
    0.07
    完善
    0.07
    塅
    0.07
     Bru
    0.07
    的一些
    0.07
    }}"↵
    0.06
    Activations Density 0.411%

    No Known Activations