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. 19-RESID-POST-AA
    6. 130550
    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
     confused
    -0.07
     patient
    -0.07
     explain
    -0.07
     Veteran
    -0.07
     addressed
    -0.07
    ب
    -0.07
    中华民族
    -0.07
    時間
    -0.07
    คำถาม
    -0.07
    撤销
    -0.06
    POSITIVE LOGITS
    庋
    0.07
    差不多
    0.07
    Param
    0.07
    Subsystem
    0.07
     ADM
    0.07
    ,ll
    0.07
    ꙳
    0.07
     seper
    0.07
     mund
    0.07
     günü
    0.07
    Activations Density 0.006%

    No Known Activations