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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 6923
    Prev
    Next
    INDEX
    Explanations

    margins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="../
    -0.07
    驴
    -0.07
    .edu
    -0.07
    秉
    -0.07
    대
    -0.07
    bt
    -0.07
    ucceed
    -0.06
    纠纷
    -0.06
    缦
    -0.06
    essed
    -0.06
    POSITIVE LOGITS
    					       
    0.08
     mnist
    0.08
    			       
    0.07
    そうで
    0.07
    )prepare
    0.07
    _dispatcher
    0.07
     серьезн
    0.07
    LIKE
    0.07
     développe
    0.07
    ثان
    0.07
    Activations Density 0.015%

    No Known Activations