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. 19-RESID-POST-AA
    6. 71529
    Prev
    Next
    INDEX
    Explanations

    Tag

    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
    _Date
    -0.08
    一栋
    -0.07
     manufacturing
    -0.07
     kurz
    -0.07
    诸葛亮
    -0.07
     swimming
    -0.07
     manufactures
    -0.06
     Furn
    -0.06
    Reserved
    -0.06
    爔
    -0.06
    POSITIVE LOGITS
     PST
    0.08
    な
    0.07
     Ability
    0.07
     metros
    0.07
    �
    0.06
     Dakota
    0.06
    难点
    0.06
    ⋋
    0.06
    遗产
    0.06
    障碍
    0.06
    Activations Density 0.002%

    No Known Activations