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. 60619
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    的研发
    -0.08
     essentially
    -0.07
    _CONST
    -0.07
    上市公司
    -0.07
    Air
    -0.07
    有必要
    -0.07
     ebooks
    -0.07
    含有
    -0.07
     Common
    -0.07
    Kat
    -0.07
    POSITIVE LOGITS
    氍
    0.08
     feather
    0.08
     baseURL
    0.07
    ENSITY
    0.07
    idar
    0.07
    blur
    0.07
    decimal
    0.07
    �
    0.07
    _tuple
    0.06
    aging
    0.06
    Activations Density 0.037%

    No Known Activations