Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 85772
    Prev
    Next
    INDEX
    Explanations

    Code and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()['
    -0.07
     السابق
    -0.07
    isVisible
    -0.07
    🖒
    -0.07
    Љ
    -0.07
    ➱
    -0.07
    Instagram
    -0.06
    -scenes
    -0.06
    쯘
    -0.06
     pomoc
    -0.06
    POSITIVE LOGITS
    却不
    0.07
    郡
    0.07
    	sub
    0.07
    词汇
    0.07
    广州
    0.07
     רב
    0.07
    也不想
    0.07
    abis
    0.06
    抱怨
    0.06
     shit
    0.06
    Activations Density 0.400%

    No Known Activations