© 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. 77441
    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
    _li
    -0.07
    것
    -0.07
    _COUNTER
    -0.07
    ight
    -0.07
     mistakenly
    -0.07
     reverse
    -0.07
    ANGLES
    -0.07
    .photos
    -0.07
     shop
    -0.07
    的技术
    -0.07
    POSITIVE LOGITS
     diploma
    0.08
     половин
    0.08
     zwłaszcza
    0.07
     verge
    0.07
     impost
    0.07
    ⊛
    0.07
    .WriteAllText
    0.07
    熛
    0.07
    戆
    0.07
    빪
    0.07
    Activations Density 0.003%

    No Known Activations