© 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. 34876
    Prev
    Next
    INDEX
    Explanations

    predict

    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
     -->↵
    -0.07
     needless
    -0.07
    [List
    -0.07
     historically
    -0.06
     seamless
    -0.06
    _EXTENDED
    -0.06
    _SPELL
    -0.06
     stained
    -0.06
    ประเทศ
    -0.06
    [jj
    -0.06
    POSITIVE LOGITS
    uje
    0.07
     Schro
    0.07
    🐻
    0.07
    space
    0.07
     Wave
    0.06
    uda
    0.06
    yellow
    0.06
    ԃ
    0.06
     zwłas
    0.06
    nova
    0.06
    Activations Density 0.048%

    No Known Activations