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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30257
    Prev
    Next
    INDEX
    Explanations

    pizza and toppings

    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
    ڍ
    -0.08
    }}],↵
    -0.07
     MDMA
    -0.07
     jav
    -0.07
    mov
    -0.07
    //}}
    -0.07
     camar
    -0.07
     fierc
    -0.07
    While
    -0.06
     vids
    -0.06
    POSITIVE LOGITS
     глаз
    0.08
    /up
    0.08
     бан
    0.07
    ktion
    0.07
    егодня
    0.07
    :bold
    0.07
     mówi
    0.07
    널
    0.07
    ionale
    0.07
     nói
    0.07
    Activations Density 0.040%

    No Known Activations