© 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. 11-RESID-POST-AA
    11. 65344
    Prev
    Next
    INDEX
    Explanations

    Claims

    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
     LAST
    -0.09
     sold
    -0.07
    	DB
    -0.07
     brings
    -0.07
     אל
    -0.07
     MST
    -0.07
    spent
    -0.07
     ending
    -0.07
    参
    -0.07
    번
    -0.07
    POSITIVE LOGITS
     openFileDialog
    0.07
     cream
    0.07
    蛞
    0.07
    _Object
    0.07
     voksne
    0.07
    ῶ
    0.07
     cottage
    0.07
     Prairie
    0.07
    機會
    0.07
    GetX
    0.07
    Activations Density 0.001%

    No Known Activations