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. 19-RESID-POST-AA
    6. 129724
    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
     max
    -0.07
    څ
    -0.07
    整天
    -0.07
     topology
    -0.07
    钪
    -0.07
    担心
    -0.07
    犨
    -0.07
     captions
    -0.07
    挤压
    -0.07
    proxy
    -0.07
    POSITIVE LOGITS
     Chall
    0.08
     Declaration
    0.07
    Stamped
    0.06
     الثلاث
    0.06
    üyor
    0.06
    遗漏
    0.06
    Ṁ
    0.06
     decency
    0.06
    שול
    0.06
     contestant
    0.06
    Activations Density 0.011%

    No Known Activations