© 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. 80394
    Prev
    Next
    INDEX
    Explanations

    Pat

    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
    -product
    -0.08
    ۃ
    -0.07
    黄色
    -0.07
    .Window
    -0.07
     Hulk
    -0.07
     Solver
    -0.06
     temp
    -0.06
    ioms
    -0.06
    drm
    -0.06
     Airbus
    -0.06
    POSITIVE LOGITS
     courtesy
    0.08
    zeichnet
    0.08
    Alt
    0.08
     emb
    0.07
     Buddy
    0.07
    getti
    0.07
    Bei
    0.07
    rift
    0.06
    ellungen
    0.06
    的孩子
    0.06
    Activations Density 0.002%

    No Known Activations