© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    Atlantic

    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
     Wo
    -0.07
    ے
    -0.07
    官兵
    -0.07
    ders
    -0.07
    其他人
    -0.07
    使用網路
    -0.07
    _online
    -0.07
    oot
    -0.07
    三家
    -0.07
     ion
    -0.07
    POSITIVE LOGITS
     Atlantic
    0.08
     `,
    0.07
     Atlantis
    0.07
    emales
    0.06
     cli
    0.06
     만나
    0.06
     لتح
    0.06
    توز
    0.06
    רוק
    0.06
    老牌
    0.06
    Activations Density 0.008%

    No Known Activations