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. 77753
    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
     Horny
    -0.07
     lonely
    -0.07
    旅游业
    -0.07
    arr
    -0.07
    _parsed
    -0.07
     scout
    -0.07
    оп
    -0.06
    matched
    -0.06
     Còn
    -0.06
    inp
    -0.06
    POSITIVE LOGITS
    骤
    0.07
     diaper
    0.07
     euth
    0.07
    ﷲ
    0.07
    院
    0.07
    _party
    0.06
    Ref
    0.06
    -New
    0.06
     deceased
    0.06
     régime
    0.06
    Activations Density 0.127%

    No Known Activations