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. 2535
    Prev
    Next
    INDEX
    Explanations

    it

    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
    sticks
    -0.08
    %,
    -0.07
     Assert
    -0.07
    鞒
    -0.07
    wu
    -0.06
    兀
    -0.06
    apeut
    -0.06
    الجزائر
    -0.06
    .fake
    -0.06
     الخبر
    -0.06
    POSITIVE LOGITS
     Ket
    0.08
    علام
    0.08
    	component
    0.07
    不同于
    0.07
     applies
    0.07
     quem
    0.07
     Guardian
    0.07
    (program
    0.07
    政府采购
    0.07
    ระ
    0.06
    Activations Density 0.327%

    No Known Activations