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. 129540
    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
    ﱔ
    -0.07
     Ferguson
    -0.07
     fighter
    -0.07
    (AF
    -0.06
     austerity
    -0.06
    .Context
    -0.06
     femme
    -0.06
    NR
    -0.06
     Suite
    -0.06
    فتر
    -0.06
    POSITIVE LOGITS
    ша
    0.07
     om
    0.07
    مهارات
    0.07
    旅程
    0.07
    万美元
    0.07
    资源
    0.06
     shoots
    0.06
    translation
    0.06
    สวย
    0.06
    _tra
    0.06
    Activations Density 0.073%

    No Known Activations