© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 3923
    Prev
    Next
    INDEX
    Explanations

    financial/legal security

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     §
    -0.07
     noticeably
    -0.07
    目前已
    -0.07
    加剧
    -0.06
    Modify
    -0.06
    쐐
    -0.06
     הסי
    -0.06
    厭
    -0.06
    褫
    -0.06
    值得关注
    -0.06
    POSITIVE LOGITS
    latin
    0.07
     salads
    0.07
    油漆
    0.07
     UPS
    0.07
    英文
    0.07
    WiFi
    0.07
    清
    0.07
    asses
    0.07
     لكل
    0.07
    大佬
    0.07
    Activations Density 0.025%

    No Known Activations