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. 44069
    Prev
    Next
    INDEX
    Explanations

    Forgetting the past

    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
    _LEG
    -0.07
    discord
    -0.07
    宝贝
    -0.06
    iteDatabase
    -0.06
     Moder
    -0.06
    REET
    -0.06
     elabor
    -0.06
    Shortcut
    -0.06
    津
    -0.06
     Traverse
    -0.06
    POSITIVE LOGITS
    玻
    0.07
    Fel
    0.07
    ős
    0.06
    Knife
    0.06
    Effective
    0.06
     GURL
    0.06
    ++)
    0.06
    带上
    0.06
    粒子
    0.06
    thic
    0.06
    Activations Density 0.031%

    No Known Activations