© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 62051
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    天生
    -0.07
    决议
    -0.07
     лег
    -0.07
    fecha
    -0.07
    负荷
    -0.07
    優惠
    -0.06
    hey
    -0.06
    隐私
    -0.06
     région
    -0.06
     munic
    -0.06
    POSITIVE LOGITS
    .ALIGN
    0.07
    (ctrl
    0.07
     cellpadding
    0.07
    _sd
    0.07
    Encryption
    0.07
     HAND
    0.07
     withString
    0.07
     wyb
    0.06
    といって
    0.06
    クロ
    0.06
    Activations Density 0.038%

    No Known Activations