© 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. 5831
    Prev
    Next
    INDEX
    Explanations

    test/train

    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
     north
    -0.08
    (rowIndex
    -0.07
     Prince
    -0.07
    ﮫ
    -0.07
    圖
    -0.07
    ʊ
    -0.07
    Е
    -0.07
    Tex
    -0.07
    苉
    -0.07
    (outputs
    -0.07
    POSITIVE LOGITS
    consistent
    0.08
     ler
    0.07
    	DWORD
    0.07
     LLVM
    0.07
     legalize
    0.07
     dalam
    0.07
    =====
    0.07
    流动
    0.07
     sự
    0.07
    复试
    0.07
    Activations Density 0.003%

    No Known Activations