Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 130930
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -vous
    -0.07
    魔术
    -0.07
    .ResponseEntity
    -0.07
    %;
    -0.07
    .raise
    -0.07
    geber
    -0.06
     longing
    -0.06
     getUsers
    -0.06
     Tesla
    -0.06
     resigned
    -0.06
    POSITIVE LOGITS
     "{$
    0.08
     pics
    0.07
     scoop
    0.07
    これまで
    0.07
    椅子
    0.06
    -Co
    0.06
    돤
    0.06
    כבד
    0.06
    climate
    0.06
     chip
    0.06
    Activations Density 0.019%

    No Known Activations