© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 5778
    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
    的各种
    -0.07
    🍛
    -0.07
    [iVar
    -0.07
     المص
    -0.07
    니다
    -0.07
     newfound
    -0.07
    odate
    -0.07
    撖
    -0.07
    ⓙ
    -0.07
    ibur
    -0.07
    POSITIVE LOGITS
    \C
    0.07
     readability
    0.07
     triumph
    0.07
     Pennsylvania
    0.07
    总工会
    0.07
     interrupt
    0.07
    datetime
    0.07
     gh
    0.07
     suppress
    0.07
     linguistic
    0.06
    Activations Density 0.004%

    No Known Activations