© 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 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. 29532
    Prev
    Next
    INDEX
    Explanations

    computer networks

    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
    nm
    -0.07
     בית
    -0.07
    >".
    -0.07
    ();
↵
↵
↵
    -0.06
    OUCH
    -0.06
    وبر
    -0.06
    eature
    -0.06
    	fr
    -0.06
     friday
    -0.06
    キャン
    -0.06
    POSITIVE LOGITS
    🏳
    0.07
    沁
    0.07
     Morse
    0.06
    折磨
    0.06
    总量
    0.06
    不可或
    0.06
    渲染
    0.06
     ADDRESS
    0.06
    新浪微博
    0.06
     Libert
    0.06
    Activations Density 0.009%

    No Known Activations