© 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. 15-RESID-POST-AA
    11. 76318
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日电
    -0.07
    בול
    -0.07
     PDT
    -0.07
     nef
    -0.07
     revealed
    -0.07
    filled
    -0.07
     MYSQL
    -0.07
    Ť
    -0.07
    �
    -0.07
    marked
    -0.06
    POSITIVE LOGITS
     Commands
    0.07
    ชำระ
    0.07
    캅
    0.07
    찝
    0.07
    הוראות
    0.07
    Charsets
    0.07
     Steps
    0.07
     العب
    0.07
    沔
    0.07
    .places
    0.07
    Activations Density 0.038%

    No Known Activations