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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 129605
    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
    집
    -0.07
    طحن
    -0.07
    ないこと
    -0.07
    之称
    -0.07
    acd
    -0.07
    _BRANCH
    -0.07
    /manual
    -0.07
     Navigate
    -0.07
    我们就
    -0.07
     Máy
    -0.07
    POSITIVE LOGITS
     ao
    0.07
     layout
    0.07
    _bbox
    0.07
    _SCHED
    0.07
    xFFFFFF
    0.06
     connections
    0.06
    .xaml
    0.06
     cl
    0.06
    ߤ
    0.06
    ELL
    0.06
    Activations Density 0.006%

    No Known Activations