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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130706
    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
    まして
    -0.07
    没错
    -0.07
     Bew
    -0.07
    相声
    -0.07
    ней
    -0.07
    _NULL
    -0.07
    _optional
    -0.06
    一贯
    -0.06
    pageNum
    -0.06
     comprom
    -0.06
    POSITIVE LOGITS
     phép
    0.07
     oppression
    0.07
    ResponseStatus
    0.07
     memiliki
    0.07
    )",
    ↵
    0.07
    shouldReceive
    0.06
    -life
    0.06
     transplant
    0.06
    	Function
    0.06
     возможность
    0.06
    Activations Density 0.103%

    No Known Activations