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. 130662
    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
     anxiety
    -0.08
     cla
    -0.07
    GLE
    -0.07
     لأ
    -0.07
    _ro
    -0.07
     predic
    -0.07
    blob
    -0.07
     grim
    -0.06
     Intersection
    -0.06
     عن
    -0.06
    POSITIVE LOGITS
     ratified
    0.07
     strm
    0.07
    技術
    0.07
    _family
    0.07
    ➧
    0.07
    UpperCase
    0.06
    を与え
    0.06
     servi
    0.06
    疗法
    0.06
    erv
    0.06
    Activations Density 0.114%

    No Known Activations