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. 7077
    Prev
    Next
    INDEX
    Explanations

    set

    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
    .cell
    -0.08
    /common
    -0.07
     Gson
    -0.07
     bulb
    -0.07
    )}
    ↵
    -0.07
    .cbo
    -0.07
    ião
    -0.07
    排行
    -0.07
     kunnen
    -0.06
    晋江
    -0.06
    POSITIVE LOGITS
    fault
    0.07
    很多朋友
    0.07
    EP
    0.07
     HttpRequest
    0.06
    ucker
    0.06
     discredit
    0.06
     Revenue
    0.06
    そこ
    0.06
    ጵ
    0.06
    oeff
    0.06
    Activations Density 0.001%

    No Known Activations