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. 27512
    Prev
    Next
    INDEX
    Explanations

    ian

    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
    اعد
    -0.07
     Há
    -0.07
     Gathering
    -0.07
    קרה
    -0.07
    ┚
    -0.07
    יג
    -0.07
    越来
    -0.07
     넘어
    -0.06
    .Yes
    -0.06
     gathers
    -0.06
    POSITIVE LOGITS
    Creation
    0.08
    整治
    0.07
     derivative
    0.07
     declaration
    0.07
     Filter
    0.07
    정보
    0.07
    考试
    0.07
     ����
    0.07
    .makedirs
    0.07
    キー
    0.07
    Activations Density 0.001%

    No Known Activations