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. 129858
    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
     toddlers
    -0.07
     -->↵
    -0.07
    stem
    -0.07
     neatly
    -0.07
    oogle
    -0.07
     gorgeous
    -0.07
    malink
    -0.07
     start
    -0.07
     square
    -0.07
    _py
    -0.07
    POSITIVE LOGITS
     المناسب
    0.08
    Ⰽ
    0.07
    /pr
    0.07
     Para
    0.07
     Orth
    0.07
    私の
    0.07
    monton
    0.07
     ISA
    0.06
    会展中心
    0.06
    储
    0.06
    Activations Density 0.011%

    No Known Activations