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. 130751
    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
    ې
    -0.07
    ulses
    -0.07
     flourishing
    -0.07
     banging
    -0.07
     Ngọc
    -0.07
    癀
    -0.07
    㹦
    -0.07
    .DataBindings
    -0.07
    square
    -0.06
    Battery
    -0.06
    POSITIVE LOGITS
    管理中心
    0.07
    rew
    0.07
    death
    0.07
    学家
    0.07
     Wales
    0.07
    something
    0.07
    绑
    0.07
    Men
    0.07
    Text
    0.07
    men
    0.07
    Activations Density 0.001%

    No Known Activations