© 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. 26176
    Prev
    Next
    INDEX
    Explanations

    special characters, symbols

    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
     poster
    -0.07
     haze
    -0.07
    大赛
    -0.07
    Squared
    -0.07
    Ⴝ
    -0.07
     '_
    -0.06
    瞬
    -0.06
    东盟
    -0.06
     OPEN
    -0.06
    AZE
    -0.06
    POSITIVE LOGITS
    可根据
    0.08
    �
    0.07
    мы
    0.07
    ataires
    0.07
     học
    0.06
    Robin
    0.06
    それぞ
    0.06
    	valid
    0.06
     sábado
    0.06
    Յ
    0.06
    Activations Density 0.057%

    No Known Activations