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. 6864
    Prev
    Next
    INDEX
    Explanations

    mechanical devices

    np_max-act-logits · gemini-2.0-flash
    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
    :]↵↵
    -0.07
    '))↵↵
    -0.07
     snatch
    -0.07
    处在
    -0.07
    chod
    -0.07
    マンション
    -0.07
    ott
    -0.06
    EmailAddress
    -0.06
    だけで
    -0.06
    ")))↵
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     gorge
    0.07
     MEM
    0.07
    ﹻ
    0.07
    (Image
    0.07
    红旗
    0.07
     Sorry
    0.07
     summary
    0.06
     hikes
    0.06
    Recorder
    0.06
    Activations Density 0.098%

    No Known Activations