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. 87109
    Prev
    Next
    INDEX
    Explanations

    pyramids and ancient structures

    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
    supplier
    -0.07
    倜
    -0.07
     Parcel
    -0.07
    _trial
    -0.07
    	lock
    -0.07
    enefit
    -0.07
    Queue
    -0.07
     stamp
    -0.06
     Prime
    -0.06
     shark
    -0.06
    POSITIVE LOGITS
     preserved
    0.08
    .feedback
    0.07
     early
    0.07
     nouvel
    0.07
    问道
    0.06
    บาล
    0.06
     closed
    0.06
     PLEASE
    0.06
     thể
    0.06
    .After
    0.06
    Activations Density 0.014%

    No Known Activations