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. 31273
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     портал
    -0.07
     pNode
    -0.07
     shortcuts
    -0.07
     pname
    -0.07
     instances
    -0.06
     froze
    -0.06
    少吃
    -0.06
    _classes
    -0.06
     Bolt
    -0.06
     vmin
    -0.06
    POSITIVE LOGITS
    urning
    0.07
    _WRONG
    0.07
    信息系统
    0.07
    �
    0.07
    ρ
    0.07
    Mouse
    0.07
    휀
    0.07
    دفاع
    0.07
    קור
    0.06
    伦敦
    0.06
    Activations Density 0.021%

    No Known Activations