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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 85552
    Prev
    Next
    INDEX
    Explanations

    positions

    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
    岁以上
    -0.07
    SUR
    -0.07
    纾
    -0.06
    Crear
    -0.06
    xCB
    -0.06
     asserting
    -0.06
    ≠
    -0.06
    =R
    -0.06
    Interrupt
    -0.06
    הר
    -0.06
    POSITIVE LOGITS
    人次
    0.07
    וסף
    0.07
     Holiday
    0.07
     사이
    0.07
    娱乐场
    0.06
    option
    0.06
     maçı
    0.06
     Orleans
    0.06
     realiza
    0.06
    一举
    0.06
    Activations Density 0.000%

    No Known Activations