© 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. 41640
    Prev
    Next
    INDEX
    Explanations

    fictional antagonists

    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
    friend
    -0.07
    HIR
    -0.07
     Każdy
    -0.07
     //--------------------------------
    -0.07
     JOptionPane
    -0.07
    łam
    -0.07
    찍
    -0.07
     mes
    -0.07
    Islamic
    -0.07
    #a
    -0.07
    POSITIVE LOGITS
    :";
    ↵
    0.08
    珋
    0.07
    蹼
    0.07
    盛会
    0.07
     vinyl
    0.07
     ocup
    0.07
     sacrific
    0.07
    (bb
    0.07
    urar
    0.07
    .ul
    0.07
    Activations Density 0.089%

    No Known Activations