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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 1976
    Prev
    Next
    INDEX
    Explanations

    ache

    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
     �
    -0.08
    인터넷
    -0.07
    SetBranchAddress
    -0.07
    :nth
    -0.07
     envelop
    -0.07
    _CSR
    -0.07
     kul
    -0.07
    _bb
    -0.07
    ideas
    -0.07
    综合
    -0.07
    POSITIVE LOGITS
    ナ
    0.07
    かも
    0.07
    ándose
    0.07
    أست
    0.07
    ające
    0.07
    здание
    0.07
    认购
    0.07
    捐款
    0.06
    _service
    0.06
    �
    0.06
    Activations Density 0.001%

    No Known Activations