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. 129581
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .Fecha
    -0.07
     tore
    -0.07
    郑州市
    -0.07
     koje
    -0.07
    -example
    -0.07
    fragment
    -0.07
     hob
    -0.06
    剧院
    -0.06
     Welcome
    -0.06
    |M
    -0.06
    POSITIVE LOGITS
    ዘ
    0.07
    NSUserDefaults
    0.07
    受欢迎
    0.06
    GameManager
    0.06
    厉害
    0.06
    Equals
    0.06
    =logging
    0.06
    疗效
    0.06
    轳
    0.06
    /Input
    0.06
    Activations Density 0.007%

    No Known Activations