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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 57668
    Prev
    Next
    INDEX
    Explanations

    references in technical documents

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    结束后
    -0.08
     faux
    -0.07
    몰
    -0.07
     contestants
    -0.07
    (ph
    -0.07
    startDate
    -0.07
    班长
    -0.07
    _ms
    -0.07
     PCI
    -0.07
     foolish
    -0.07
    POSITIVE LOGITS
    ![
    0.07
     علم
    0.07
    mek
    0.06
     intermediary
    0.06
     function
    0.06
     ViewModel
    0.06
     Yak
    0.06
    Mate
    0.06
     Cake
    0.06
    تسم
    0.06
    Activations Density 0.012%

    No Known Activations