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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 131011
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (tf
    -0.07
    的时间
    -0.07
    맍
    -0.07
     weer
    -0.07
    靺
    -0.07
    .assertIn
    -0.06
     gleich
    -0.06
    oque
    -0.06
    赇
    -0.06
    .Logf
    -0.06
    POSITIVE LOGITS
    sett
    0.08
    焘
    0.07
    管理局
    0.06
     السياس
    0.06
    Ann
    0.06
    enville
    0.06
     superclass
    0.06
    选取
    0.06
    ListBox
    0.06
     가지
    0.06
    Activations Density 0.092%

    No Known Activations