Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109619
    Prev
    Next
    INDEX
    Explanations

    storage

    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
    ક
    -0.07
    ะ
    -0.07
    ﴘ
    -0.07
    电源
    -0.06
     OK
    -0.06
     Đối
    -0.06
     toc
    -0.06
    칟
    -0.06
    )",↵
    -0.06
     Deck
    -0.06
    POSITIVE LOGITS
     않을
    0.07
     Roulette
    0.07
    셧
    0.07
    更快
    0.07
    教え
    0.07
    findBy
    0.07
     breadcrumbs
    0.07
     Raised
    0.07
     Shotgun
    0.07
    改制
    0.06
    Activations Density 0.059%

    No Known Activations