© 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
    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. 29780
    Prev
    Next
    INDEX
    Explanations

    health advice, safety

    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
     לרכוש
    -0.07
     examined
    -0.07
     devoted
    -0.07
    脱贫攻坚
    -0.07
     Symptoms
    -0.07
    	assert
    -0.07
     thành
    -0.07
    土豆
    -0.06
    赌博
    -0.06
    ulas
    -0.06
    POSITIVE LOGITS
     viewers
    0.07
    �
    0.07
    鋈
    0.07
     FR
    0.07
    .scheme
    0.07
    )[-
    0.07
    网讯
    0.07
    +E
    0.07
    璈
    0.07
    (statement
    0.06
    Activations Density 0.054%

    No Known Activations