© 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. 57519
    Prev
    Next
    INDEX
    Explanations

    ogram

    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
    justice
    -0.07
    Validation
    -0.07
    非常的
    -0.07
    es
    -0.07
     바로
    -0.07
    แด
    -0.06
     isChecked
    -0.06
    EndTime
    -0.06
    مرحلة
    -0.06
    ホ
    -0.06
    POSITIVE LOGITS
    ,z
    0.08
     UM
    0.07
    尽早
    0.07
    etter
    0.07
     mHandler
    0.07
     מוצר
    0.07
     tempting
    0.06
     remain
    0.06
    	va
    0.06
    ogram
    0.06
    Activations Density 0.003%

    No Known Activations