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. 2724
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
     Stefan
    -0.07
    들
    -0.07
     infer
    -0.07
    �
    -0.06
     الأخ
    -0.06
     Devices
    -0.06
     أمس
    -0.06
     Redux
    -0.06
     üz
    -0.06
     viêm
    -0.06
    POSITIVE LOGITS
    министр
    0.07
    _MOD
    0.07
    ("(%
    0.07
     Parenthood
    0.07
    .enumer
    0.07
     Según
    0.06
    壁画
    0.06
     denomin
    0.06
    _DGRAM
    0.06
    DH
    0.06
    Activations Density 0.043%

    No Known Activations