© 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. 115840
    Prev
    Next
    INDEX
    Explanations

    interference

    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_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
    คอย
    -0.07
    トン
    -0.07
    ощ
    -0.07
    สอบ
    -0.07
    �
    -0.07
     staat
    -0.07
    そう
    -0.06
    лег
    -0.06
     conveying
    -0.06
    去
    -0.06
    POSITIVE LOGITS
    sdale
    0.07
     Storm
    0.07
    施策
    0.07
    查询
    0.07
    -fw
    0.07
    也可
    0.07
     childs
    0.07
    _include
    0.06
    	Spring
    0.06
     ucfirst
    0.06
    Activations Density 0.043%

    No Known Activations