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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 31035
    Prev
    Next
    INDEX
    Explanations

    0 or 5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    时任
    -0.07
    -inc
    -0.07
    非常重要
    -0.07
    _when
    -0.07
     magn
    -0.07
    Suit
    -0.07
    itempty
    -0.07
    melon
    -0.07
    phy
    -0.07
     Vect
    -0.06
    POSITIVE LOGITS
     doğum
    0.07
    活动
    0.07
    姿势
    0.07
    荨
    0.07
     owed
    0.07
     soaked
    0.07
     месте
    0.06
    Ⰽ
    0.06
    𝖛
    0.06
    数据
    0.06
    Activations Density 0.002%

    No Known Activations