© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 62269
    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
     falsely
    -0.07
    Fel
    -0.07
    .Cross
    -0.07
    奇
    -0.06
     verg
    -0.06
    🐃
    -0.06
    ensus
    -0.06
    ceed
    -0.06
    过分
    -0.06
    ("(%
    -0.06
    POSITIVE LOGITS
    iga
    0.08
     Biggest
    0.07
     gating
    0.07
    呗
    0.07
     abortion
    0.07
     tops
    0.07
    胺
    0.07
    _WORK
    0.06
     música
    0.06
    严重的
    0.06
    Activations Density 0.001%

    No Known Activations