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. 72443
    Prev
    Next
    INDEX
    Explanations

    Discussion of similarities

    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
     ballet
    -0.08
     RecyclerView
    -0.07
    (android
    -0.07
     trend
    -0.07
    柴纳
    -0.07
     tended
    -0.07
    四大
    -0.07
     breakthrough
    -0.07
    	total
    -0.06
     trou
    -0.06
    POSITIVE LOGITS
    不要太
    0.07
    둥
    0.07
    egr
    0.07
    arious
    0.07
     AIS
    0.07
    葆
    0.07
    эр
    0.06
    代言人
    0.06
    的位置
    0.06
    uum
    0.06
    Activations Density 0.072%

    No Known Activations