© 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. 11-RESID-POST-AA
    6. 127565
    Prev
    Next
    INDEX
    Explanations

    coding and databases

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ترو
    -0.08
    啰
    -0.07
    marginLeft
    -0.07
    -directory
    -0.07
     Nhận
    -0.07
    ファン
    -0.07
    LoggedIn
    -0.07
     reconoc
    -0.06
     oppos
    -0.06
    莿
    -0.06
    POSITIVE LOGITS
    oms
    0.08
     IOC
    0.08
    ARY
    0.07
    ;.
    0.07
     -:
    0.07
    욱
    0.07
     Liga
    0.07
     aging
    0.07
     vid
    0.07
    imento
    0.07
    Activations Density 0.195%

    No Known Activations