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. 110028
    Prev
    Next
    INDEX
    Explanations

    data representation

    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
    ges
    -0.06
    	map
    -0.06
     distance
    -0.06
    ble
    -0.06
    .month
    -0.06
    .Length
    -0.06
    絲
    -0.06
     validity
    -0.06
    cle
    -0.06
     CCP
    -0.06
    POSITIVE LOGITS
    เ
    0.07
    应该怎么
    0.07
    ACTER
    0.07
    HomeController
    0.07
     לעבור
    0.07
    ActionButton
    0.07
    企
    0.07
    -custom
    0.06
    ribbon
    0.06
    asper
    0.06
    Activations Density 0.007%

    No Known Activations