© 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. 15-RESID-POST-AA
    6. 48422
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hungarian
    -0.07
     Sikh
    -0.07
    宗教
    -0.07
     Brunswick
    -0.07
    aki
    -0.07
    uka
    -0.07
     nerve
    -0.07
    "][$
    -0.06
    SKI
    -0.06
    ⇝
    -0.06
    POSITIVE LOGITS
     Serif
    0.07
     Mort
    0.07
    샾
    0.07
     Tud
    0.06
    	case
    0.06
    投
    0.06
    -menu
    0.06
    笑意
    0.06
    ثمان
    0.06
    support
    0.06
    Activations Density 0.006%

    No Known Activations