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. 36411
    Prev
    Next
    INDEX
    Explanations

    conflict and insurgency

    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
    (lbl
    -0.07
     mills
    -0.07
     xmm
    -0.07
     flavorful
    -0.07
    團隊
    -0.07
    amt
    -0.07
    _iface
    -0.07
    メント
    -0.07
     Providers
    -0.06
    领取
    -0.06
    POSITIVE LOGITS
     depressing
    0.08
    Press
    0.07
     battleground
    0.07
    淠
    0.07
    beans
    0.07
     تص
    0.07
     journals
    0.07
    جاب
    0.07
    Scar
    0.07
    砝
    0.06
    Activations Density 0.031%

    No Known Activations