© 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. 11-RESID-POST-AA
    11. 87566
    Prev
    Next
    INDEX
    Explanations

    have

    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
     explic
    -0.08
     Stacy
    -0.07
    .nlm
    -0.07
    urry
    -0.07
     plur
    -0.07
     adulte
    -0.06
     Face
    -0.06
     sauce
    -0.06
     dummy
    -0.06
     Yaz
    -0.06
    POSITIVE LOGITS
    ':[
    0.08
    =L
    0.07
    分别是
    0.07
    沙发上
    0.07
     UB
    0.07
    .Perform
    0.07
    地中
    0.07
     glands
    0.07
     высоко
    0.07
    书院
    0.07
    Activations Density 0.200%

    No Known Activations