© 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. 19-RESID-POST-AA
    11. 68745
    Prev
    Next
    INDEX
    Explanations

    analysis and investigation

    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
    'al
    -0.07
    Kİ
    -0.07
    А
    -0.07
    developers
    -0.07
    裴
    -0.06
    -party
    -0.06
    딘
    -0.06
    ᴘ
    -0.06
    ptides
    -0.06
    倘
    -0.06
    POSITIVE LOGITS
     mq
    0.07
    Nr
    0.07
     Câm
    0.07
    增强了
    0.07
    下降
    0.07
    讲述
    0.07
    入侵
    0.07
     saf
    0.06
    阑
    0.06
     Largest
    0.06
    Activations Density 0.003%

    No Known Activations