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. 15-RESID-POST-AA
    6. 77763
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    了很多
    -0.07
    陀
    -0.07
    흫
    -0.07
    _("
    -0.06
    ☓
    -0.06
     chociaż
    -0.06
    rates
    -0.06
    referrer
    -0.06
    副主任
    -0.06
    heet
    -0.06
    POSITIVE LOGITS
    岸
    0.08
    .per
    0.07
    赁
    0.07
    	typ
    0.07
    aqu
    0.07
    .Ab
    0.07
    .lineEdit
    0.07
     ').
    0.07
     nen
    0.07
    graphql
    0.07
    Activations Density 0.035%

    No Known Activations