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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 89525
    Prev
    Next
    INDEX
    Explanations

    Class

    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
     בנוגע
    -0.07
    eurs
    -0.07
     converting
    -0.06
    משך
    -0.06
     territor
    -0.06
    春节
    -0.06
    EventHandler
    -0.06
    极度
    -0.06
    続き
    -0.06
     çı
    -0.06
    POSITIVE LOGITS
    治愈
    0.08
    損害
    0.07
     gauge
    0.07
    =[];↵
    0.07
     disadvantages
    0.07
    softmax
    0.07
    正确的
    0.07
    聘用
    0.07
     Rails
    0.07
    괸
    0.07
    Activations Density 0.001%

    No Known Activations