© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 70092
    Prev
    Next
    INDEX
    Explanations

    safe

    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
     interv
    -0.07
    �
    -0.07
    那是
    -0.07
    inputs
    -0.06
    atural
    -0.06
    <dd
    -0.06
    诺贝尔
    -0.06
     canceled
    -0.06
    届
    -0.06
     immigration
    -0.06
    POSITIVE LOGITS
    确定
    0.08
     CGRect
    0.07
    使劲
    0.07
    长江
    0.07
     minced
    0.06
    等
    0.06
    GUI
    0.06
    	dest
    0.06
    一个重要
    0.06
     sucking
    0.06
    Activations Density 0.009%

    No Known Activations