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. 57376
    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
    owered
    -0.08
    "default
    -0.07
    aven
    -0.07
     smaller
    -0.07
    igger
    -0.07
    弟子
    -0.07
    大纲
    -0.07
     antis
    -0.07
    omedical
    -0.06
     iterations
    -0.06
    POSITIVE LOGITS
    writer
    0.07
     kes
    0.07
     çift
    0.07
     Tip
    0.07
    צפי
    0.07
    �
    0.06
     signing
    0.06
    -terrorism
    0.06
     إلي
    0.06
    tón
    0.06
    Activations Density 0.122%

    No Known Activations