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. 2661
    Prev
    Next
    INDEX
    Explanations

    You

    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
    alyzed
    -0.07
     loses
    -0.07
    .beans
    -0.06
     heater
    -0.06
    ↜
    -0.06
    ana
    -0.06
     предост
    -0.06
    ux
    -0.06
     provisions
    -0.06
     shortcuts
    -0.06
    POSITIVE LOGITS
    理念
    0.08
    跨
    0.07
    >}↵
    0.07
    pires
    0.07
    累
    0.07
    继
    0.06
    步
    0.06
    -\
    0.06
    olini
    0.06
    ład
    0.06
    Activations Density 0.069%

    No Known Activations