Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 26091
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intervention
    -0.07
    aurant
    -0.07
     flag
    -0.07
    .ensure
    -0.07
     imagin
    -0.07
    运营商
    -0.07
    \Middleware
    -0.07
    directive
    -0.07
    _Helper
    -0.07
    .Are
    -0.07
    POSITIVE LOGITS
     Notícias
    0.08
    anj
    0.07
    /memory
    0.07
    瑧
    0.07
    -te
    0.07
    年起
    0.07
    arters
    0.07
    année
    0.07
    dać
    0.06
    ﺓ
    0.06
    Activations Density 0.041%

    No Known Activations