© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 90114
    Prev
    Next
    INDEX
    Explanations

    Numerical data and percentages

    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
     frustr
    -0.07
    	gpio
    -0.07
    指挥
    -0.07
     yeni
    -0.07
    {i
    -0.06
     colore
    -0.06
    posição
    -0.06
    anguard
    -0.06
    ysics
    -0.06
     adress
    -0.06
    POSITIVE LOGITS
    应收账款
    0.08
    @testable
    0.08
    阶段
    0.07
    AppBundle
    0.07
    🐨
    0.07
     erfol
    0.07
     Eagle
    0.07
    _revision
    0.07
     doGet
    0.07
    稂
    0.07
    Activations Density 0.069%

    No Known Activations