Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 46482
    Prev
    Next
    INDEX
    Explanations

    <

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agility
    -0.07
    涨停
    -0.07
     Ginger
    -0.07
     china
    -0.07
    _dataset
    -0.07
    ܕ
    -0.07
    老兵
    -0.07
    莙
    -0.07
     grape
    -0.06
     ähnlich
    -0.06
    POSITIVE LOGITS
     CODE
    0.07
                                     
    0.07
     Uncomment
    0.07
    ifice
    0.07
     QUI
    0.06
     BUSINESS
    0.06
     SUB
    0.06
    (U
    0.06
     (_
    0.06
    䏝
    0.06
    Activations Density 0.001%

    No Known Activations