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. 2765
    Prev
    Next
    INDEX
    Explanations

    diverse and philosophical texts

    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
     invoice
    -0.08
     özel
    -0.07
     defaults
    -0.07
     القاهرة
    -0.07
    _old
    -0.07
    معرف
    -0.07
    _male
    -0.07
     chrono
    -0.07
     donné
    -0.07
    これを
    -0.07
    POSITIVE LOGITS
     Heath
    0.08
    �
    0.07
    渴望
    0.07
    BOR
    0.07
    媲
    0.07
    W
    0.07
    pread
    0.06
     ideologies
    0.06
    ظ
    0.06
    生怕
    0.06
    Activations Density 0.022%

    No Known Activations