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. 23-RESID-POST-AA
    6. 130242
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parency
    -0.07
    ทำ
    -0.07
    -white
    -0.06
    akit
    -0.06
    走了
    -0.06
    太子
    -0.06
     đựng
    -0.06
    �
    -0.06
     thẳng
    -0.06
     facility
    -0.06
    POSITIVE LOGITS
    (enum
    0.07
     liking
    0.07
    .At
    0.06
    ::*;↵
    0.06
    互补
    0.06
     enum
    0.06
    TAB
    0.06
    %B
    0.06
    尋
    0.06
     Includes
    0.06
    Activations Density 0.773%

    No Known Activations