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. 27612
    Prev
    Next
    INDEX
    Explanations

    Medical studies, patients

    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
    级
    -0.07
    经典
    -0.07
     aware
    -0.07
     ABC
    -0.07
     Presenter
    -0.06
    广西
    -0.06
     nuestros
    -0.06
     Micro
    -0.06
    克思主义
    -0.06
     bliss
    -0.06
    POSITIVE LOGITS
    /operator
    0.07
    dr
    0.07
    .values
    0.07
    iks
    0.07
    ForEach
    0.07
     thử
    0.07
    واجه
    0.07
     BOTH
    0.07
    egative
    0.06
    _operations
    0.06
    Activations Density 0.029%

    No Known Activations