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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 115316
    Prev
    Next
    INDEX
    Explanations

    technical questions and dimensions

    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
    Eventually
    -0.07
    出身
    -0.07
    落叶
    -0.07
    HasMaxLength
    -0.06
     чего
    -0.06
    槍
    -0.06
    স
    -0.06
     Gauss
    -0.06
     jung
    -0.06
    Everybody
    -0.06
    POSITIVE LOGITS
    -held
    0.08
    彷
    0.07
    ��
    0.07
    Ṭ
    0.07
    -type
    0.06
    ölü
    0.06
    OLUTE
    0.06
    _tmp
    0.06
     mức
    0.06
     Datos
    0.06
    Activations Density 0.245%

    No Known Activations