Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36041
    Prev
    Next
    INDEX
    Explanations

    studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cushion
    -0.07
    _graphics
    -0.06
    /*@
    -0.06
     gson
    -0.06
    فئ
    -0.06
    bek
    -0.06
    creature
    -0.06
     chim
    -0.06
    뎌
    -0.06
    cestor
    -0.06
    POSITIVE LOGITS
    股价
    0.09
    utzt
    0.07
    	flag
    0.07
     Infect
    0.07
    _IW
    0.07
    雇佣
    0.07
    myp
    0.07
    番
    0.07
    حاول
    0.07
    快速
    0.07
    Activations Density 0.190%

    No Known Activations