© 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. 77919
    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
    (Me
    -0.07
     Lam
    -0.07
    цион
    -0.07
     ah
    -0.06
    ，默认
    -0.06
    usion
    -0.06
     conveniently
    -0.06
    (num
    -0.06
     MyApp
    -0.06
    պ
    -0.06
    POSITIVE LOGITS
     welding
    0.07
     Ronaldo
    0.07
    /goto
    0.07
    lda
    0.07
    _TRIANGLE
    0.07
    ]=='
    0.06
    自在
    0.06
    otton
    0.06
    EqualityComparer
    0.06
    进入到
    0.06
    Activations Density 0.031%

    No Known Activations