© 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. 7-RESID-POST-AA
    6. 80101
    Prev
    Next
    INDEX
    Explanations

    German language

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Settings
    -0.08
     endanger
    -0.07
     ATTR
    -0.07
    𝓅
    -0.07
    有个
    -0.07
     chaotic
    -0.07
     mgr
    -0.07
     vmin
    -0.07
    Eta
    -0.07
    dp
    -0.06
    POSITIVE LOGITS
    "I
    0.07
    ruise
    0.07
    ሎ
    0.07
    בק
    0.07
    担保
    0.07
    ば
    0.07
    Href
    0.07
    ancell
    0.07
    指南
    0.07
    РИ
    0.06
    Activations Density 0.007%

    No Known Activations