© 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. 11-RESID-POST-AA
    6. 34945
    Prev
    Next
    INDEX
    Explanations

    color spaces and luminance

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -sup
    -0.08
    整
    -0.07
    堆
    -0.07
     AMS
    -0.07
    abee
    -0.07
    ORIZ
    -0.07
    _font
    -0.07
     Joey
    -0.07
     stuffing
    -0.07
     optimize
    -0.07
    POSITIVE LOGITS
    𝕋
    0.07
     선
    0.07
    _RETURNTRANSFER
    0.07
    _singleton
    0.07
    	last
    0.07
     lehet
    0.06
    ហ
    0.06
     becoming
    0.06
    心理咨询
    0.06
     resizeMode
    0.06
    Activations Density 0.031%

    No Known Activations