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. 71790
    Prev
    Next
    INDEX
    Explanations

    non-English 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
    �
    -0.07
     loads
    -0.07
     når
    -0.07
     fullPath
    -0.06
    奠定
    -0.06
     //------------------------------------------------
    -0.06
    handleRequest
    -0.06
    ][-
    -0.06
    ฃ
    -0.06
    됌
    -0.06
    POSITIVE LOGITS
    微笑
    0.09
    ergus
    0.08
    导师
    0.08
    RuntimeException
    0.08
    微妙
    0.07
    ิด
    0.07
    mię
    0.07
     Meditation
    0.07
    ü
    0.07
    GRE
    0.07
    Activations Density 0.216%

    No Known Activations