© 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. 7-RESID-POST-AA
    11. 103098
    Prev
    Next
    INDEX
    Explanations

    Nagar

    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
     하는
    -0.07
    變
    -0.07
    虛
    -0.07
     intermittent
    -0.06
    委屈
    -0.06
    接收
    -0.06
    �
    -0.06
    用途
    -0.06
     גר
    -0.06
    /tasks
    -0.06
    POSITIVE LOGITS
     cauliflower
    0.08
     cif
    0.07
    签名
    0.07
    ](
    0.06
     Tata
    0.06
     mmc
    0.06
     :\
    0.06
    iasm
    0.06
    °C
    0.06
     largely
    0.06
    Activations Density 0.002%

    No Known Activations