© 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 EvalsExportsinterp-engineNEWAPI 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. 129709
    Prev
    Next
    INDEX
    Explanations

    Questions/speculation

    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
    将来
    -0.07
    /vendor
    -0.07
     Rough
    -0.07
    Aaron
    -0.07
    Ͳ
    -0.07
    בוע
    -0.07
    -Time
    -0.06
    _THIS
    -0.06
    蔫
    -0.06
    Asked
    -0.06
    POSITIVE LOGITS
     ž
    0.08
    物
    0.07
     Bir
    0.07
     الرياض
    0.07
    /path
    0.07
     başına
    0.07
    弆
    0.07
    公司的
    0.07
     cadena
    0.07
     무
    0.07
    Activations Density 0.052%

    No Known Activations