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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 30076
    Prev
    Next
    INDEX
    Explanations

    Physics models

    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
     hind
    -0.08
    navbarDropdown
    -0.07
    化解
    -0.07
     самостоя
    -0.07
     fal
    -0.07
    Viol
    -0.07
     attendant
    -0.07
     rue
    -0.07
    valuator
    -0.07
    :id
    -0.07
    POSITIVE LOGITS
    Μ
    0.07
     bracelet
    0.07
    حلول
    0.07
    adding
    0.07
     musica
    0.07
    齊
    0.07
    ılan
    0.07
    }/${
    0.06
    esan
    0.06
     affinity
    0.06
    Activations Density 0.004%

    No Known Activations