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. 56718
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     culture
    -0.07
    马来
    -0.07
     sacrificed
    -0.07
    _ack
    -0.07
    析
    -0.07
    政
    -0.06
    _Image
    -0.06
    讽刺
    -0.06
     Karma
    -0.06
    礼
    -0.06
    POSITIVE LOGITS
    (HttpStatus
    0.07
    Usually
    0.07
    StreamReader
    0.06
    国防部
    0.06
    מכשיר
    0.06
    DDevice
    0.06
    obar
    0.06
    잃
    0.06
    ᶜ
    0.06
    ייעוץ
    0.06
    Activations Density 0.067%

    No Known Activations