© 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. 49397
    Prev
    Next
    INDEX
    Explanations

    minute

    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
     Sudoku
    -0.07
     Alleg
    -0.07
     Drawable
    -0.07
    alance
    -0.07
     proport
    -0.07
    -live
    -0.07
    	Rect
    -0.07
    /li
    -0.07
    注意力
    -0.07
    blood
    -0.07
    POSITIVE LOGITS
     mogę
    0.08
     mots
    0.08
    启用
    0.07
     minute
    0.07
    חינ
    0.07
    員工
    0.07
    诞生
    0.07
     que
    0.07
     chant
    0.07
     Thousands
    0.07
    Activations Density 0.007%

    No Known Activations