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. 109953
    Prev
    Next
    INDEX
    Explanations

    -

    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
     phys
    -0.07
     Cos
    -0.07
     McD
    -0.07
     invaluable
    -0.07
    慈
    -0.07
     tanggal
    -0.07
    "G
    -0.07
    不好意思
    -0.07
    不该
    -0.07
     بداية
    -0.07
    POSITIVE LOGITS
     superiority
    0.07
    ],↵
    0.07
    OURCE
    0.07
    ewear
    0.06
    ())
    ↵
    0.06
    izza
    0.06
     środow
    0.06
     '');↵
    0.06
    ()>↵
    0.06
    机组
    0.06
    Activations Density 0.000%

    No Known Activations