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. 88208
    Prev
    Next
    INDEX
    Explanations

    torchvision

    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
     nud
    -0.07
    迄
    -0.07
    まぁ
    -0.07
    ällt
    -0.06
     Ging
    -0.06
    ufig
    -0.06
     impe
    -0.06
    _ctxt
    -0.06
    依法
    -0.06
    转入
    -0.06
    POSITIVE LOGITS
    棉
    0.07
    特定
    0.07
    	           
    0.07
    лик
    0.07
    _DIRECTORY
    0.07
    म
    0.07
    パート
    0.07
    yclopedia
    0.07
    Н
    0.07
    梦
    0.07
    Activations Density 0.001%

    No Known Activations