© 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. 127657
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    悚
    -0.08
     disruptions
    -0.08
     gửi
    -0.07
    線
    -0.07
     disaster
    -0.07
    dfs
    -0.07
    riteria
    -0.07
    的问题
    -0.07
    picable
    -0.07
     Industries
    -0.07
    POSITIVE LOGITS
     Doll
    0.07
    économie
    0.07
    Following
    0.07
     olmuş
    0.06
    HAND
    0.06
     denomin
    0.06
     instructor
    0.06
     Flower
    0.06
    ⛱
    0.06
     practice
    0.06
    Activations Density 0.004%

    No Known Activations