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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130876
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strerror
    -0.07
    "Just
    -0.07
    :key
    -0.07
     Matcher
    -0.06
     להת
    -0.06
    (Entity
    -0.06
     сосед
    -0.06
     stav
    -0.06
    睄
    -0.06
    一度
    -0.06
    POSITIVE LOGITS
    posta
    0.07
    疲劳
    0.07
     $"
    0.07
     yatırım
    0.06
    线索
    0.06
    马
    0.06
     ))}↵
    0.06
    وى
    0.06
    ento
    0.06
    )null
    0.06
    Activations Density 0.079%

    No Known Activations