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. 36143
    Prev
    Next
    INDEX
    Explanations

    disproven stories

    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
     Howard
    -0.07
    XPath
    -0.07
     الدكت
    -0.07
    clientId
    -0.07
    .RecyclerView
    -0.07
     Qty
    -0.07
    -phase
    -0.07
     Taste
    -0.07
    -notes
    -0.07
     Ferdinand
    -0.06
    POSITIVE LOGITS
    dex
    0.07
    gun
    0.07
    퍽
    0.07
    QRSTUVWXYZ
    0.07
     showers
    0.07
    LOSS
    0.07
    ἵ
    0.07
    سكر
    0.07
    _Num
    0.07
    تقييم
    0.06
    Activations Density 0.056%

    No Known Activations