© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 62205
    Prev
    Next
    INDEX
    Explanations

    straw man argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    契合
    -0.08
    (loss
    -0.07
     ge
    -0.07
     Checkout
    -0.07
     battle
    -0.07
    _rot
    -0.06
    悬
    -0.06
    division
    -0.06
    移
    -0.06
    ▩
    -0.06
    POSITIVE LOGITS
     hakkı
    0.08
    DonaldTrump
    0.07
    ksen
    0.07
    浏览器
    0.06
    _chance
    0.06
    تكنولوج
    0.06
     UserId
    0.06
    אופן
    0.06
    beschäft
    0.06
    .toList
    0.06
    Activations Density 0.001%

    No Known Activations