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

    Neuronpedia

    APICircuit 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. 48505
    Prev
    Next
    INDEX
    Explanations

    polar coordinates

    np_max-act-logits · gemini-2.0-flash
    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
    سوف
    -0.07
     Ethnic
    -0.07
    審
    -0.07
    念佛
    -0.07
    藜
    -0.07
    [axis
    -0.07
    �
    -0.07
    	option
    -0.06
    -ac
    -0.06
    做事
    -0.06
    POSITIVE LOGITS
    ]>=
    0.08
     **)&
    0.07
     {}↵↵↵
    0.07
    歌词
    0.07
     ding
    0.07
    ()/
    0.07
     ?>/
    0.07
    ...)↵
    0.06
    inx
    0.06
    quin
    0.06
    Activations Density 0.007%

    No Known Activations