© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23697
    Prev
    Next
    INDEX
    Explanations

    Then

    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
    Of
    -0.08
    ($('
    -0.07
    Board
    -0.07
    al
    -0.07
     towards
    -0.07
     Breaking
    -0.07
     import
    -0.07
     המשחק
    -0.07
    זול
    -0.07
    报送
    -0.07
    POSITIVE LOGITS
     then
    0.11
     Paran
    0.08
    Then
    0.07
     затем
    0.07
    /set
    0.07
     Then
    0.07
     ц
    0.07
     fascinated
    0.07
    .Then
    0.07
    	lua
    0.07
    Activations Density 0.104%

    No Known Activations