© 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. 8818
    Prev
    Next
    INDEX
    Explanations

    "be right back"

    np_max-act-logits · gemini-2.0-flash
    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
     essential
    -0.07
     Donetsk
    -0.07
    irsch
    -0.07
    全力以赴
    -0.07
    ész
    -0.06
    pository
    -0.06
    兴趣
    -0.06
    蕾
    -0.06
    ốt
    -0.06
    assel
    -0.06
    POSITIVE LOGITS
    行业的
    0.07
    panion
    0.07
     ú
    0.07
    Tuple
    0.07
    itest
    0.07
     ResourceManager
    0.07
    ,SIGNAL
    0.07
     smugg
    0.07
    长短
    0.07
    床
    0.06
    Activations Density 0.013%

    No Known Activations