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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 129681
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    וכל
    -0.07
     Â
    -0.07
     urls
    -0.07
     pron
    -0.07
    מוס
    -0.06
    <{
    -0.06
    rored
    -0.06
    ἠ
    -0.06
    んじゃない
    -0.06
     Civilization
    -0.06
    POSITIVE LOGITS
     zusammen
    0.08
    bones
    0.07
    続けて
    0.07
    �
    0.07
     Zusammen
    0.07
     selber
    0.06
    淮
    0.06
    Hostname
    0.06
    よね
    0.06
    ProductName
    0.06
    Activations Density 0.001%

    No Known Activations