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. 87847
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    _DIG
    -0.07
    功能性
    -0.07
     MAN
    -0.07
    �
    -0.07
     hade
    -0.07
    se
    -0.07
     �
    -0.06
     MSS
    -0.06
    }<
    -0.06
    阽
    -0.06
    POSITIVE LOGITS
     delegate
    0.08
     verschiedenen
    0.08
    上赛季
    0.08
    划算
    0.07
     рассказал
    0.07
    整治
    0.07
    试点
    0.07
    黹
    0.07
    我们应该
    0.07
     QObject
    0.07
    Activations Density 0.003%

    No Known Activations