© 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. 4768
    Prev
    Next
    INDEX
    Explanations

    Code-related

    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
     provoke
    -0.08
     Levine
    -0.08
    4
    -0.07
    -viol
    -0.07
    ຄ
    -0.07
     various
    -0.07
    .convert
    -0.07
     Der
    -0.07
    _ATOMIC
    -0.07
     vrai
    -0.07
    POSITIVE LOGITS
    .setBackground
    0.08
     ImageIcon
    0.07
    idUser
    0.07
    进驻
    0.07
    .present
    0.06
     понрав
    0.06
    臺南市
    0.06
    利用您的
    0.06
     QtAws
    0.06
     LoggerFactory
    0.06
    Activations Density 0.003%

    No Known Activations