© 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. 20830
    Prev
    Next
    INDEX
    Explanations

    were

    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
     singly
    -0.07
     counselling
    -0.07
     therapist
    -0.07
    (phone
    -0.07
     mw
    -0.07
    selling
    -0.06
     measuring
    -0.06
     pwd
    -0.06
    -semibold
    -0.06
     overse
    -0.06
    POSITIVE LOGITS
     Rowe
    0.08
    acy
    0.08
    让我们
    0.08
    棵树
    0.07
     rates
    0.07
    WebView
    0.07
    cke
    0.07
    更好的
    0.07
    给我
    0.07
    课本
    0.07
    Activations Density 0.001%

    No Known Activations