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. 15-RESID-POST-AA
    6. 14351
    Prev
    Next
    INDEX
    Explanations

    innocent

    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
     Đề
    -0.07
    带头
    -0.07
    黄河
    -0.07
    כה
    -0.07
    elsen
    -0.07
    _receipt
    -0.06
    abel
    -0.06
    导航
    -0.06
    变成
    -0.06
    _pemb
    -0.06
    POSITIVE LOGITS
     innocence
    0.09
     innocent
    0.08
    ⚔
    0.08
    ginas
    0.07
     |--
    0.07
    (contract
    0.07
    子弹
    0.07
    נשים
    0.07
    Windows
    0.07
     있다
    0.07
    Activations Density 0.003%

    No Known Activations