© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 75569
    Prev
    Next
    INDEX
    Explanations

    can may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     начал
    -0.07
    来的
    -0.07
    更是
    -0.07
    来看看
    -0.07
    来
    -0.07
    来进行
    -0.06
    加上
    -0.06
    两年
    -0.06
    上了
    -0.06
     Polynomial
    -0.06
    POSITIVE LOGITS
    ReturnType
    0.07
    _free
    0.07
    博物馆
    0.07
    _choices
    0.07
    manage
    0.07
    物质
    0.07
    Manifest
    0.07
    分行
    0.06
     używa
    0.06
    _BOOT
    0.06
    Activations Density 0.060%

    No Known Activations