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. 19-RESID-POST-AA
    6. 130532
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    now
    -0.07
    nf
    -0.07
    人数
    -0.07
    ertain
    -0.07
    region
    -0.07
    eff
    -0.07
    缩
    -0.07
    Configure
    -0.07
    rons
    -0.07
     detail
    -0.07
    POSITIVE LOGITS
    捌
    0.07
    โฮ
    0.07
    _business
    0.07
    璨
    0.07
     Hao
    0.07
     cabin
    0.07
     truck
    0.07
    绔
    0.07
    营
    0.07
    总公司
    0.07
    Activations Density 0.023%

    No Known Activations