© 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. 15-RESID-POST-AA
    6. 89580
    Prev
    Next
    INDEX
    Explanations

    select

    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
     longitudinal
    -0.06
    口中
    -0.06
     voll
    -0.06
    Progress
    -0.06
    绕
    -0.06
    	sort
    -0.06
    	handle
    -0.06
     Roberts
    -0.06
    というのが
    -0.06
     elong
    -0.06
    POSITIVE LOGITS
     LABEL
    0.07
    redients
    0.07
     нужны
    0.07
    Credit
    0.07
     CPUs
    0.07
    ılı
    0.07
    mighty
    0.06
     restaurant
    0.06
    哥们
    0.06
    ckså
    0.06
    Activations Density 0.042%

    No Known Activations