© 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. 40098
    Prev
    Next
    INDEX
    Explanations

    in

    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
     élè
    -0.07
    FieldValue
    -0.07
    Ê
    -0.07
    솤
    -0.07
     Ensure
    -0.07
    learning
    -0.07
    工具
    -0.07
    普及
    -0.07
     dtype
    -0.07
    模范
    -0.07
    POSITIVE LOGITS
     IR
    0.07
     geld
    0.07
     موجود
    0.07
    仄
    0.07
    ဟ
    0.07
    	priv
    0.07
     BEGIN
    0.06
     lid
    0.06
     startDate
    0.06
    .SelectCommand
    0.06
    Activations Density 0.031%

    No Known Activations