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. 61729
    Prev
    Next
    INDEX
    Explanations

    Asterisks and slashes

    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
     suitability
    -0.07
    𦝼
    -0.07
    خص
    -0.07
    悆
    -0.06
     диз
    -0.06
    浑
    -0.06
     משתמש
    -0.06
     regulations
    -0.06
    𬨎
    -0.06
    핼
    -0.06
    POSITIVE LOGITS
    本报讯
    0.07
     getDefault
    0.07
    sword
    0.07
    罾
    0.07
    .carousel
    0.07
    .states
    0.07
     htons
    0.07
    ().'
    0.06
    -ticket
    0.06
    委托
    0.06
    Activations Density 0.014%

    No Known Activations