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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 68945
    Prev
    Next
    INDEX
    Explanations

    which

    np_max-act-logits · gemini-2.0-flash
    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
     anew
    -0.07
    奇妙
    -0.07
    -lang
    -0.07
     centerX
    -0.07
     Phaser
    -0.07
    dług
    -0.06
    竣工
    -0.06
    .notify
    -0.06
    初二
    -0.06
    Blue
    -0.06
    POSITIVE LOGITS
    хи
    0.07
    ("--
    0.07
    单位
    0.07
     jlong
    0.07
     Produk
    0.06
    ancel
    0.06
    -variable
    0.06
     MACHINE
    0.06
    _${
    0.06
    三是
    0.06
    Activations Density 0.020%

    No Known Activations