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. 61820
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    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
    _Map
    -0.09
     Adv
    -0.08
    _Check
    -0.07
     Exam
    -0.07
    Ban
    -0.07
    red
    -0.07
     nn
    -0.07
    🐑
    -0.06
     Tow
    -0.06
     fmap
    -0.06
    POSITIVE LOGITS
     coaster
    0.08
     substrate
    0.07
    stars
    0.07
     substit
    0.07
    قضي
    0.07
    音乐会
    0.07
    手持
    0.07
     cougar
    0.07
     حقوق
    0.07
    眼科
    0.07
    Activations Density 0.004%

    No Known Activations