© 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. 91634
    Prev
    Next
    INDEX
    Explanations

    am

    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
    เน
    -0.07
     Hwy
    -0.07
     Byz
    -0.07
     enormously
    -0.07
    隧道
    -0.07
    ẍ
    -0.06
    伸
    -0.06
    xdf
    -0.06
    ฮอ
    -0.06
    葵
    -0.06
    POSITIVE LOGITS
     morality
    0.07
     MAL
    0.07
    quip
    0.07
    _detect
    0.07
     Chem
    0.07
    (Process
    0.07
    opes
    0.07
    imates
    0.07
     '}';↵
    0.06
    CardContent
    0.06
    Activations Density 0.002%

    No Known Activations