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. 15-RESID-POST-AA
    6. 121295
    Prev
    Next
    INDEX
    Explanations

    short-circuiting

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assets
    -0.07
    EATURE
    -0.07
     Crime
    -0.07
     Army
    -0.07
    filled
    -0.07
    rieving
    -0.07
    樹
    -0.06
     Measures
    -0.06
    موا
    -0.06
    Crypto
    -0.06
    POSITIVE LOGITS
    怎么说
    0.08
    菲律宾
    0.08
    少爷
    0.07
    oord
    0.07
    上海市
    0.07
     GLsizei
    0.07
    〆
    0.07
    〛
    0.07
     polo
    0.07
     básico
    0.07
    Activations Density 0.039%

    No Known Activations