Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 130809
    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
    Leg
    -0.08
    兜
    -0.07
    edom
    -0.07
    ☽
    -0.07
     dataSet
    -0.07
     Thickness
    -0.07
    可以使
    -0.06
    麋
    -0.06
    seek
    -0.06
    .deep
    -0.06
    POSITIVE LOGITS
     sarcast
    0.07
     Architect
    0.07
     Nu
    0.07
     tier
    0.07
     ию
    0.07
     Syntax
    0.06
     niveau
    0.06
    :",↵
    0.06
    단
    0.06
    ό
    0.06
    Activations Density 0.003%

    No Known Activations